CN110378860B - Method, device, computer equipment and storage medium for repairing video - Google Patents
Method, device, computer equipment and storage medium for repairing video Download PDFInfo
- Publication number
- CN110378860B CN110378860B CN201910692753.6A CN201910692753A CN110378860B CN 110378860 B CN110378860 B CN 110378860B CN 201910692753 A CN201910692753 A CN 201910692753A CN 110378860 B CN110378860 B CN 110378860B
- Authority
- CN
- China
- Prior art keywords
- repaired
- video frame
- preset
- algorithm
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000012545 processing Methods 0.000 claims abstract description 122
- 230000006378 damage Effects 0.000 claims abstract description 111
- 230000008439 repair process Effects 0.000 claims abstract description 106
- 230000008832 photodamage Effects 0.000 claims abstract description 7
- 230000006735 deficit Effects 0.000 claims description 40
- 230000009467 reduction Effects 0.000 claims description 32
- 230000003321 amplification Effects 0.000 claims description 27
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 27
- 230000000694 effects Effects 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 10
- 230000015654 memory Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 30
- 230000000903 blocking effect Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000011946 reduction process Methods 0.000 description 4
- 230000009528 severe injury Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010348 incorporation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Picture Signal Circuits (AREA)
Abstract
The disclosure relates to a method, a device, computer equipment and a storage medium for repairing video, and belongs to the technical field of video processing. The method comprises the following steps: obtaining a video frame to be repaired; determining the image quality damage degree of a video frame to be repaired; if the image quality damage degree of the video frame to be repaired is greater than or equal to a preset damage degree threshold, performing first repair processing on the video frame to be repaired through at least one repair algorithm according to the serious damage repair sequence; if the image quality damage degree of the video frame to be repaired is smaller than a preset damage degree threshold, performing second repair processing on the video frame to be repaired through at least one repair algorithm according to the light damage repair sequence. After the video frames to be repaired are distinguished, the video frames to be repaired can be repaired according to different repairing sequences through at least one repairing algorithm, the repairing process is more targeted, and the obtained repaired video frames are higher in image quality.
Description
Technical Field
The present disclosure relates to the field of video processing technology, and in particular, to a method, an apparatus, a computer device, and a storage medium for repairing video.
Background
In the process of encoding the original video and transmitting the encoded video, the image quality of the original video is inevitably damaged due to different factors. These factors mainly include blocking, loss of edge information, loss of detail information, incorporation of non-artificial noise, etc. After decoding the encoded video, the decoded video has poor image quality relative to the original video.
Disclosure of Invention
In order to overcome the problems in the related art, the present disclosure provides the following technical solutions:
according to a first aspect of embodiments of the present disclosure, there is provided a method of repairing video, the method comprising:
obtaining a video frame to be repaired;
determining the image quality damage degree of the video frame to be repaired;
if the image quality damage degree of the video frame to be repaired is greater than or equal to a preset damage degree threshold, performing first repair processing on the video frame to be repaired through at least one repair algorithm according to the severe damage repair sequence;
and if the image quality damage degree of the video frame to be repaired is smaller than the preset damage degree threshold, performing second repair processing on the video frame to be repaired through at least one repair algorithm according to the light damage repair sequence.
Optionally, the determining the image quality impairment degree of the video frame to be repaired includes:
determining at least one image quality impairment algorithm;
calculating the image quality damage degree of the video frame to be repaired through each image quality damage degree algorithm respectively to obtain sub-image quality damage degrees corresponding to each image quality damage degree algorithm respectively;
and carrying out weighted summation on the quality impairment degree of each sub-image to obtain the quality impairment degree of the video frame to be repaired.
Optionally, the performing, by at least one repair algorithm, a first repair process on the video frame to be repaired according to the severe damage repair order includes:
performing deblocking processing on the video frame to be repaired through a preset deblocking algorithm;
after the video frame to be repaired is subjected to deblocking treatment, amplifying the video frame to be repaired after the deblocking treatment according to a first preset amplification factor by a preset super-resolution algorithm;
after amplifying the video frame to be repaired after the deblocking processing, if the sharpening degree of the video frame to be repaired after the amplifying processing is smaller than a preset sharpening degree threshold value, sharpening the video frame to be repaired after the amplifying processing through a preset sharpening algorithm;
After the video frame to be repaired after the amplification treatment is sharpened, if the noise value in the video frame to be repaired after the sharpening treatment is greater than a preset noise threshold value, the noise reduction treatment is carried out on the video frame to be repaired after the sharpening treatment through a preset noise reduction algorithm.
Optionally, the performing, by at least one repair algorithm, a second repair process on the video frame to be repaired according to the light damaged repair order includes:
amplifying the video frame to be repaired according to a second preset amplification factor by a preset super-resolution algorithm;
after the video frame to be repaired is amplified, performing deblocking processing on the amplified video frame to be repaired by a preset deblocking algorithm;
after performing deblocking processing on the video frame to be repaired after the amplification processing, if the sharpening degree of the video frame to be repaired after the deblocking processing is smaller than a preset sharpening degree threshold value, performing sharpening processing on the video frame to be repaired after the deblocking processing through a preset sharpening algorithm;
after sharpening the video frame to be repaired after the deblocking processing, if the noise value in the video frame to be repaired after the sharpening processing is greater than a preset noise threshold value, carrying out noise reduction processing on the video frame to be repaired after the sharpening processing through a preset noise reduction algorithm.
Optionally, the video format of the video to which the video frame to be repaired belongs is YUV format.
According to a second aspect of embodiments of the present disclosure, there is provided an apparatus for repairing video, the apparatus comprising:
the acquisition module is used for acquiring the video frame to be repaired;
the determining module is used for determining the image quality damage degree of the video frame to be repaired;
the repair module is used for performing first repair processing on the video frame to be repaired through at least one repair algorithm according to the severe damage repair sequence when the image quality damage degree of the video frame to be repaired is greater than or equal to a preset damage degree threshold value; and when the image quality damage degree of the video frame to be repaired is smaller than the preset damage degree threshold, performing second repair processing on the video frame to be repaired through at least one repair algorithm according to the light damage repair sequence.
Optionally, the determining module is configured to:
determining at least one image quality impairment algorithm;
calculating the image quality damage degree of the video frame to be repaired through each image quality damage degree algorithm respectively to obtain sub-image quality damage degrees corresponding to each image quality damage degree algorithm respectively;
and carrying out weighted summation on the quality impairment degree of each sub-image to obtain the quality impairment degree of the video frame to be repaired.
Optionally, the repair module is configured to:
performing deblocking processing on the video frame to be repaired through a preset deblocking algorithm;
after the video frame to be repaired is subjected to deblocking treatment, amplifying the video frame to be repaired after the deblocking treatment according to a first preset amplification factor by a preset super-resolution algorithm;
after amplifying the video frame to be repaired after the deblocking processing, if the sharpening degree of the video frame to be repaired after the amplifying processing is smaller than a preset sharpening degree threshold value, sharpening the video frame to be repaired after the amplifying processing through a preset sharpening algorithm;
after the video frame to be repaired after the amplification treatment is sharpened, if the noise value in the video frame to be repaired after the sharpening treatment is greater than a preset noise threshold value, the noise reduction treatment is carried out on the video frame to be repaired after the sharpening treatment through a preset noise reduction algorithm.
Optionally, the repair module is configured to:
amplifying the video frame to be repaired according to a second preset amplification factor by a preset super-resolution algorithm;
After the video frame to be repaired is amplified, performing deblocking processing on the amplified video frame to be repaired by a preset deblocking algorithm;
after performing deblocking processing on the video frame to be repaired after the amplification processing, if the sharpening degree of the video frame to be repaired after the deblocking processing is smaller than a preset sharpening degree threshold value, performing sharpening processing on the video frame to be repaired after the deblocking processing through a preset sharpening algorithm;
after sharpening the video frame to be repaired after the deblocking processing, if the noise value in the video frame to be repaired after the sharpening processing is greater than a preset noise threshold value, carrying out noise reduction processing on the video frame to be repaired after the sharpening processing through a preset noise reduction algorithm.
Optionally, the video format of the video to which the video frame to be repaired belongs is YUV format.
According to a third aspect of embodiments of the present disclosure, there is provided a computer device comprising a processor, a communication interface, a memory, and a communication bus, wherein:
the processor, the communication interface and the memory complete communication with each other through the communication bus;
The memory is used for storing a computer program;
the processor is configured to execute the program stored in the memory, so as to implement the method for repairing video.
According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium having stored therein a computer program which, when executed by a processor, implements the method of repairing video described above.
The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects:
in the embodiment of the disclosure, any video frame to be repaired can be repaired, and the image quality of the repaired video frame is improved compared with that of the video frame before repair. Meanwhile, the embodiment of the disclosure can distinguish the video frames to be repaired based on the image quality damage degree of different video frames to be repaired, if the image quality damage degree is higher, the video frames to be repaired are seriously damaged video frames, and if the image quality damage degree is lower, the video frames to be repaired are slightly damaged video frames. After distinguishing the video frames to be repaired, the video frames to be repaired can be repaired through at least one repair algorithm according to different repair sequences, the repair treatment is more targeted, and the obtained repaired video frames have higher image quality.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. In the drawings:
FIG. 1 is a schematic diagram of a system for repairing video, according to an exemplary embodiment;
FIG. 2 is a schematic diagram of an apparatus for repairing video according to an exemplary embodiment;
FIG. 3 is a flow chart illustrating a method of repairing video according to an exemplary embodiment;
FIG. 4 is a flow chart illustrating a method of repairing video according to an exemplary embodiment;
FIG. 5 is a flow diagram illustrating a method of repairing video according to an exemplary embodiment;
FIG. 6 is a flow chart illustrating a method of repairing video according to an exemplary embodiment;
FIG. 7 is a flow chart illustrating a method of repairing video according to an exemplary embodiment;
FIG. 8 is a flow chart illustrating a method of repairing video according to an exemplary embodiment;
FIG. 9 is a schematic diagram illustrating an apparatus for repairing video according to an exemplary embodiment;
fig. 10 is a schematic diagram of a computer device, according to an example embodiment.
Specific embodiments of the present disclosure have been shown by way of the above drawings and will be described in more detail below. These drawings and the written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the disclosed concepts to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
Embodiments of the present disclosure provide a method of repairing video, which may be implemented by a computer device. In one possible implementation manner, in a system for repairing video, as shown in fig. 1, a video server, a repair video server and a terminal may be provided, and the number of the video server, the repair video server and the terminal may be plural, and in the embodiment of the present disclosure, one video server, one repair video server and one terminal are described as an example. In a video server, a large number of videos may be stored, which may be present for different factors or in the case of a light or heavy image quality impairment. If the video with the image quality damage condition is directly shared to the terminal for users to enjoy, the user experience is reduced, and the watching effect is affected, so before the video with the image quality damage condition is shared to the terminal, the video server can send any video to be repaired to the repair video server, and the repair video server can repair any video to be repaired. After the repair video server performs repair processing on any video to be repaired, the repair video server can share the repaired video after the repair processing to a terminal for users to enjoy, so that the user experience and the viewing quality can be improved.
In the repair video server, a video repair processing framework may be provided. As shown in fig. 2, the video repair processing framework may include a video input module, a decoding module, a source analysis module, a pre-processing module, an encoding module, and a video output module. The method for repairing video provided by the embodiment of the disclosure can be executed in the preprocessing module.
The decoding module may be configured to decode the encoded video to obtain a decoded video in YUV (a color coding method, "Y" represents brightness luminence, "U" and "V" represent chroma luminence) format. The source analysis module can be used for analyzing the basic attribute, the high-level semantic and the high-level characteristic of the video so as to better determine the characteristic of the video, and further can assist other modules to exert the maximum effect of the other modules. The preprocessing module can be used for processing data of the YUV format video through an image or video processing technology, so that subjective visual effects of the processed video advance towards a direction which can be perceived by human eyes, a direction in which image quality is improved and a direction in which the image quality is enhanced. The coding module can be used for compressing the video in the YUV format to obtain the coded video, so that the data volume of the coded video is far smaller than the data volume of the original video, and in the process of transmitting the coded video, the bandwidth consumption can be saved, and the network transmission is facilitated. The video output module may be generally used to output a video having the same resolution as the original video, but in the embodiment of the present disclosure, the video output module may be used to output a video having a resolution greater than the resolution of the original video, so that the problem of loss of details in the video may be solved, and by introducing the super-resolution sub-module, the resolution of the original video is improved, and the specific final resolution of the video depends on the magnification set in the super-resolution sub-module.
An exemplary embodiment of the present disclosure provides a method for repairing video, as shown in fig. 3, a process flow of the method may include the following steps:
step S301, a video frame to be repaired is acquired.
In implementations, a computer device may obtain video frames to be repaired, which may be one of the video frames to be repaired, each of which may include a plurality of video frames. Optionally, the video format of the video to which the video frame to be repaired belongs may be YUV format.
Step S302, determining the image quality impairment of the video frame to be repaired.
In implementations, a computer device may calculate a quality impairment of a video frame to be repaired. The quality impairment of the repair video frame may reflect the severity of the blockiness of the video frame to be repaired. The image quality impairment of the video frame to be repaired may be represented by an expression F (I) =score_block, where score_block is the image quality impairment of the video frame to be repaired, and the function F may represent one or more image quality impairment algorithms. In practical application, different image quality damage algorithms can evaluate the image quality damage of the video frame from different reference angles, the evaluation effect is different, one image quality damage algorithm can be selected, the image quality damage of the video frame to be repaired can be calculated, multiple image quality damage algorithms can be selected, and the image quality damage of the video frame to be repaired can be jointly calculated.
Optionally, step S302 may include: determining at least one image quality impairment algorithm; calculating the image quality damage degree of the video frame to be repaired through each image quality damage degree algorithm respectively to obtain sub-image quality damage degrees corresponding to each image quality damage degree algorithm respectively; and carrying out weighted summation on the quality impairment degree of each sub-image to obtain the quality impairment degree of the video frame to be repaired.
In the implementation, the image quality damage degree of the video frame to be repaired is calculated jointly by selecting a plurality of image quality damage degree algorithms, and the image quality damage degree of the video frame can be evaluated from a plurality of reference angles, so that the effects of different evaluation modes can be integrated. The computer equipment can determine at least one image quality damage degree algorithm, respectively calculate the image quality damage degree of the video frame to be repaired through each image quality damage degree algorithm to obtain sub-image quality damage degrees respectively corresponding to each image quality damage degree algorithm, and perform weighted summation on each sub-image quality damage degree to obtain the image quality damage degree of the video frame to be repaired. The weights corresponding to different image quality damage algorithms can be set according to requirements.
Step S303, judging whether the video frame to be repaired is seriously damaged or slightly damaged based on the image quality damage degree of the video frame to be repaired.
In implementation, as shown in fig. 4, an image quality analysis module may be disposed in the computer device, and the image quality analysis module may determine whether the video frame to be repaired is severely damaged or lightly damaged based on the image quality damage degree of the video frame to be repaired. If the video frame to be repaired is severely damaged, the video frame to be repaired is input into a severely damaged repair module for repair processing, and if the video frame to be repaired is lightly damaged, the video frame to be repaired is input into a lightly damaged repair module for repair processing.
Step S304, if the image quality damage degree of the video frame to be repaired is greater than or equal to a preset damage degree threshold, the video frame to be repaired is severely damaged, and the first repair processing is performed on the video frame to be repaired through at least one repair algorithm according to the severely damaged repair sequence.
Step S305, if the image quality damage degree of the video frame to be repaired is smaller than the preset damage degree threshold, the video frame to be repaired is slightly damaged, and the second repair processing is performed on the video frame to be repaired through at least one repair algorithm according to the slightly damaged repair sequence.
In implementation, when the video frame to be repaired is severely damaged or slightly damaged, at least one repair algorithm correspondingly used may be the same or different, but in the process of repairing the video frame to be repaired by using at least one repair algorithm, the sequence of repairing the video frame to be repaired by using the repair algorithm is different, and the following embodiments will describe the sequence of different repair processes of the video frame to be repaired with different damage degrees in detail.
In the embodiment of the disclosure, any video frame to be repaired can be repaired, and the image quality of the repaired video frame is improved compared with that of the video frame before repair. Meanwhile, the embodiment of the disclosure can distinguish the video frames to be repaired based on the image quality damage degree of different video frames to be repaired, if the image quality damage degree is higher, the video frames to be repaired are seriously damaged video frames, and if the image quality damage degree is lower, the video frames to be repaired are slightly damaged video frames. After distinguishing the video frames to be repaired, the video frames to be repaired can be repaired through at least one repair algorithm according to different repair sequences, the repair treatment is more targeted, and the obtained repaired video frames have higher image quality.
Based on the same inventive concept, an exemplary embodiment of the present disclosure provides a method of repairing video, as shown in fig. 5, a process flow of the method may include the steps of:
in step S501, a video frame to be repaired is acquired.
In implementations, a computer device may obtain video frames to be repaired, which may be one of the video frames to be repaired, each of which may include a plurality of video frames. Optionally, the video format of the video to which the video frame to be repaired belongs may be YUV format.
Step S502, determining the image quality impairment degree of the video frame to be repaired.
In implementations, a computer device may calculate a quality impairment of a video frame to be repaired. The quality impairment of the repair video frame may reflect the severity of the blockiness of the video frame to be repaired. The image quality impairment of the video frame to be repaired may be represented by an expression F (I) =score_block, where score_block is the image quality impairment of the video frame to be repaired, and the function F may represent one or more image quality impairment algorithms. In practical application, different image quality damage algorithms can evaluate the image quality damage of the video frame from different reference angles, the evaluation effect is different, one image quality damage algorithm can be selected, the image quality damage of the video frame to be repaired can be calculated, multiple image quality damage algorithms can be selected, and the image quality damage of the video frame to be repaired can be jointly calculated.
In step S503, if the image quality damage degree of the video frame to be repaired is greater than or equal to the preset damage degree threshold, it is determined that the video frame to be repaired is severely damaged.
In implementation, if it is determined that the video frame to be repaired is severely damaged, the first repair process may be performed on the video frame to be repaired through at least one repair algorithm, where the at least one repair algorithm may include a deblocking algorithm, a super resolution algorithm, a sharpening algorithm, and a noise reduction algorithm, and the algorithms sequentially corresponding to the at least one repair algorithm may be denoted as an AR algorithm, an SR algorithm, an MS algorithm, and a DE algorithm.
Step S504, performing deblocking processing on the video frame to be repaired by a preset deblocking algorithm.
In implementation, as shown in fig. 6, the computer device may obtain a video frame a to be repaired included in the video in YUV format, and may remove a blocking effect in the video frame a to be repaired by using an AR algorithm, to obtain a video frame B to be repaired.
In step S505, after the deblocking processing is performed on the video frame to be repaired, the video frame to be repaired after the deblocking processing is performed is amplified according to the first preset amplification factor by using a preset super-resolution algorithm.
In implementation, an SR algorithm may be used to amplify the video frame B to be repaired to obtain the video frame C to be repaired. The magnification may be scale, which may be set to 1 or a value greater than 1. If scale is set to 1, the amplification process may not be performed, and the video frame to be repaired C is the video frame to be repaired B. If the video frame B to be repaired needs to be amplified, the scale can be set to 2, 3 and other values.
Step S506, after the video frame to be repaired after the deblocking processing is amplified, if the sharpening degree of the video frame to be repaired after the amplifying processing is less than the preset sharpening degree threshold, the video frame to be repaired after the amplifying processing is sharpened by a preset sharpening algorithm.
In implementation, an MS algorithm may be used to sharpen the video frame C to be repaired, to obtain the video frame D to be repaired. Firstly, the sharpening degree of the video frame C to be repaired can be judged, if the sharpening degree of the video frame C to be repaired is greater than or equal to a preset sharpening degree threshold thr_sharp, sharpening processing can not be performed, and the video frame D to be repaired is the video frame C to be repaired. If the sharpening degree of the video frame C to be repaired is smaller than thr_sharp, an MS algorithm can be adopted to sharpen the video frame C to be repaired. The sharpening degree may be represented by a G (I) =score_share expression, where score_share is the sharpening degree of the video frame C to be repaired.
Step S507, after the sharpening process is performed on the video frame to be repaired after the amplifying process, if the noise value in the video frame to be repaired after the sharpening process is greater than the preset noise threshold, performing a noise reduction process on the video frame to be repaired after the sharpening process through a preset noise reduction algorithm.
In implementation, a DE algorithm may be used to perform noise reduction processing on the video frame D to be repaired, to obtain the video frame E to be repaired. Firstly, the noise value of the video frame E to be repaired can be determined, if the noise value of the video frame E to be repaired is less than or equal to the preset noise threshold thr_noise, sharpening processing may not be performed, and the video frame E to be repaired is the video frame D to be repaired. If the noise value of the video frame D to be repaired is larger than thr_noise, a DE algorithm can be adopted to perform noise reduction treatment on the video frame D to be repaired. The noise value may be represented by an expression N (I) =score_noise, where score_noise is the noise value of the video frame D to be repaired.
In the above process, some details in the original video frame are erased by the deblocking algorithm, and the details can be supplemented in the video frame by the super-resolution algorithm, so that the video frame is amplified, but at the same time, noise is amplified. For severely corrupted video frames to be repaired, i.e. video frames with a relatively large existing blocking effect, they may visually appear to have a significant mosaic or a relatively large number of mosaics. For the video frame to be repaired, the blocking effect in the video frame to be repaired can be reduced through a deblocking algorithm, for example, the number of mosaics can be reduced or the mosaics can be eliminated, and then details are supplemented in the video frame to be repaired after the deblocking processing through a super-resolution algorithm. Otherwise, if the super-resolution processing is performed first, the amplification processing is similar to the amplification processing of the video frame to be repaired, the original serious blockiness in the video frame to be repaired can be amplified, the blockiness in the video frame to be repaired after the super-resolution processing can be more obvious, and the specific expression can be that the mosaic is more serious. Later, the more serious blocking effect in the video frame to be repaired after super-resolution processing is removed by a blocking-effect removing algorithm, and at the moment, the blocking effect is difficult to be removed cleanly by the blocking-effect removing algorithm. In addition, if the original blocking effect of the video frame to be repaired is larger, for the same deblocking algorithm, the effect of removing the blocking effect in the video frame with smaller size is better than the effect of removing the blocking effect in the video frame with larger size, so that the effect of removing the video frame to be repaired before super-resolution processing is better as much as possible.
In addition, the edge of the video frame to be repaired can be repaired more sharply and more clearly, and the contour lines are more obvious through sharpening, but noise can be sharpened while the edge is sharpened, so that in the embodiment of the disclosure, the edge can be sharpened first and then noise can be reduced, and in the noise reduction process, some details in the video frame are inevitably removed.
Taking the texture on the clothes as an example, the texture of the clothes can be regarded as edge information, if the noise reduction treatment is carried out on the texture of the clothes, the texture of the clothes can be removed more or less, and then even if the texture of the clothes is sharpened, the removed texture of the clothes cannot be recovered. If the texture of the garment is removed, there is no object that can be sharpened. However, if the texture of the garment is sharpened first, the texture of the garment may be preserved and reinforced. At this time, although noise is also sharpened, noise before and after sharpening can be removed by noise reduction processing in the following.
In the embodiment of the disclosure, any video frame to be repaired can be repaired, and the image quality of the repaired video frame is improved compared with that of the video frame before repair. Meanwhile, the embodiment of the disclosure can distinguish the video frames to be repaired based on the image quality damage degree of different video frames to be repaired, if the image quality damage degree is higher, the video frames to be repaired are seriously damaged video frames, and if the image quality damage degree is lower, the video frames to be repaired are slightly damaged video frames. After distinguishing the video frames to be repaired, the video frames to be repaired can be repaired through at least one repair algorithm according to different repair sequences, the repair treatment is more targeted, and the obtained repaired video frames have higher image quality.
Based on the same inventive concept, an exemplary embodiment of the present disclosure provides a method of repairing video, as shown in fig. 7, a process flow of which may include the steps of:
step S701, obtaining a video frame to be repaired.
In implementations, a computer device may obtain video frames to be repaired, which may be one of the video frames to be repaired, each of which may include a plurality of video frames. Optionally, the video format of the video to which the video frame to be repaired belongs may be YUV format.
Step S702, determining the image quality impairment degree of the video frame to be repaired.
In implementations, a computer device may calculate a quality impairment of a video frame to be repaired. The quality impairment of the repair video frame may reflect the severity of the blockiness of the video frame to be repaired. The image quality impairment of the video frame to be repaired may be represented by an expression F (I) =score_block, where score_block is the image quality impairment of the video frame to be repaired, and the function F may represent one or more image quality impairment algorithms. In practical application, different image quality damage algorithms can evaluate the image quality damage of the video frame from different reference angles, the evaluation effect is different, one image quality damage algorithm can be selected, the image quality damage of the video frame to be repaired can be calculated, multiple image quality damage algorithms can be selected, and the image quality damage of the video frame to be repaired can be jointly calculated.
In step S703, if the image quality damage degree of the video frame to be repaired is less than the preset damage degree threshold, it is determined that the video frame to be repaired is slightly damaged.
In implementation, if it is determined that the video frame to be repaired is lightly damaged, a second repair process may be performed on the video frame to be repaired through at least one repair algorithm, where the at least one repair algorithm may include a deblocking algorithm, a super resolution algorithm, a sharpening algorithm, and a noise reduction algorithm, and the algorithms sequentially corresponding to the at least one repair algorithm may be denoted as an AR algorithm, an SR algorithm, an MS algorithm, and a DE algorithm.
Step S704, amplifying the video frame to be repaired according to a second preset amplification factor through a preset super-resolution algorithm.
In implementation, as shown in fig. 8, the computer device may obtain a video frame a to be repaired included in the video in YUV format, and may amplify the video frame a to be repaired by using an SR algorithm to obtain a video frame B to be repaired. The magnification may be scale, which may be set to 1 or a value greater than 1. If scale is set to 1, the amplification process may not be performed, and the video frame to be repaired B is the video frame to be repaired a. If the video frame A to be repaired needs to be amplified, the scale can be set to 2, 3 and other values.
Step S705, after the video frame to be repaired is amplified, the amplified video frame to be repaired is subjected to the deblocking process by a preset deblocking algorithm.
In implementation, an AR algorithm may be used to remove the blocking effect in the video frame B to be repaired, to obtain the video frame C to be repaired.
Step S706, after performing the deblocking process on the video frame to be repaired after the amplification process, if the sharpening degree of the video frame to be repaired after the deblocking process is less than the preset sharpening degree threshold, performing the sharpening process on the video frame to be repaired after the deblocking process by using a preset sharpening algorithm.
In implementation, an MS algorithm may be used to sharpen the video frame C to be repaired, to obtain the video frame D to be repaired. Firstly, the sharpening degree of the video frame C to be repaired can be judged, if the sharpening degree of the video frame C to be repaired is greater than or equal to a preset sharpening degree threshold thr_sharp, sharpening processing can not be performed, and the video frame D to be repaired is the video frame C to be repaired. If the sharpening degree of the video frame C to be repaired is smaller than thr_sharp, an MS algorithm can be adopted to sharpen the video frame C to be repaired. The sharpening degree may be represented by a G (I) =score_share expression, where score_share is the sharpening degree of the video frame C to be repaired.
Step S707, after the sharpening process is performed on the video frame to be repaired after the deblocking process, if the noise value in the video frame to be repaired after the sharpening process is greater than the preset noise threshold, the noise reduction process is performed on the video frame to be repaired after the sharpening process by the preset noise reduction algorithm.
In implementation, a DE algorithm may be used to perform noise reduction processing on the video frame D to be repaired, to obtain the video frame E to be repaired. Firstly, the noise value of the video frame E to be repaired can be determined, if the noise value of the video frame E to be repaired is less than or equal to the preset noise threshold thr_noise, sharpening processing may not be performed, and the video frame E to be repaired is the video frame D to be repaired. If the noise value of the video frame D to be repaired is larger than thr_noise, a DE algorithm can be adopted to perform noise reduction treatment on the video frame D to be repaired. The noise value may be represented by an expression N (I) =score_noise, where score_noise is the noise value of the video frame D to be repaired.
In the above process, some details in the original video frame are erased by the deblocking algorithm, and the details can be supplemented in the video frame by the super-resolution algorithm, so that the video frame is amplified, but at the same time, noise is amplified. For a slightly damaged video frame to be repaired, namely a video frame with a smaller blocking effect, super-resolution processing can be performed first, and the original blocking effect in the video frame to be repaired is smaller, so that the blocking effect in the video frame to be repaired is not obviously aggravated even if the super-resolution processing is performed first. After super-resolution processing is carried out on the video frame to be repaired, the effect of supplementing details in the video frame to be repaired can be achieved. Then, the video frame to be repaired after super-resolution processing can be subjected to deblocking processing through a deblocking algorithm. Although some details in the original video frame can be erased by the deblocking algorithm, since a great amount of details are already supplemented in the video frame to be repaired by super-resolution processing in advance, even in the deblocking processing, details in some video frames to be repaired after super-resolution processing are removed, and finally, the details can be kept much more than those in the video frame before repair processing.
Conversely, for lightly corrupted video frames, they are of relatively good quality and relatively rich in detail. If the deblocking process is performed first and then the super-resolution process is performed, the deblocking process smoothes the original abundant details in the slightly damaged video frame to be repaired, so that the difficulty in recovering the details of the video frame in the super-resolution process is increased. Namely, for the slightly damaged video frame to be repaired, subtraction is firstly carried out and then addition is carried out, so that the obtained effect is not ideal. Because of the better quality video frames, more attention is paid to the increase in detail during the repair process. The blocking effect of the video frames with better image quality is originally small, and the visual perception of the blocking effect by the audience is not obvious.
In addition, the edge of the video frame to be repaired can be repaired more sharply and more clearly, and the contour lines are more obvious through sharpening, but noise can be sharpened while the edge is sharpened, so that in the embodiment of the disclosure, the edge can be sharpened first and then noise can be reduced, and in the noise reduction process, some details in the video frame are inevitably removed.
Taking the texture on the clothes as an example, the texture of the clothes can be regarded as edge information, if the noise reduction treatment is carried out on the texture of the clothes, the texture of the clothes can be removed more or less, and then even if the texture of the clothes is sharpened, the removed texture of the clothes cannot be recovered. If the texture of the garment is removed, there is no object that can be sharpened. However, if the texture of the garment is sharpened first, the texture of the garment may be preserved and reinforced. At this time, although noise is also sharpened, noise before and after sharpening can be removed by noise reduction processing in the following.
In the embodiment of the disclosure, any video frame to be repaired can be repaired, and the image quality of the repaired video frame is improved compared with that of the video frame before repair. Meanwhile, the embodiment of the disclosure can distinguish the video frames to be repaired based on the image quality damage degree of different video frames to be repaired, if the image quality damage degree is higher, the video frames to be repaired are seriously damaged video frames, and if the image quality damage degree is lower, the video frames to be repaired are slightly damaged video frames. After distinguishing the video frames to be repaired, the video frames to be repaired can be repaired through at least one repair algorithm according to different repair sequences, the repair treatment is more targeted, and the obtained repaired video frames have higher image quality.
Yet another exemplary embodiment of the present disclosure provides an apparatus for repairing video, as shown in fig. 9, the apparatus including:
an obtaining module 910, configured to obtain a video frame to be repaired;
a determining module 920, configured to determine an image quality impairment degree of the video frame to be repaired;
the repair module 930 is configured to perform a first repair process on the video frame to be repaired by at least one repair algorithm according to a severe damage repair sequence when the image quality damage degree of the video frame to be repaired is greater than or equal to a preset damage degree threshold; and when the image quality damage degree of the video frame to be repaired is smaller than the preset damage degree threshold, performing second repair processing on the video frame to be repaired through at least one repair algorithm according to the light damage repair sequence.
Optionally, the determining module 920 is configured to:
determining at least one image quality impairment algorithm;
calculating the image quality damage degree of the video frame to be repaired through each image quality damage degree algorithm respectively to obtain sub-image quality damage degrees corresponding to each image quality damage degree algorithm respectively;
and carrying out weighted summation on the quality impairment degree of each sub-image to obtain the quality impairment degree of the video frame to be repaired.
Optionally, the repair module 930 is configured to:
performing deblocking processing on the video frame to be repaired through a preset deblocking algorithm;
after the video frame to be repaired is subjected to deblocking treatment, amplifying the video frame to be repaired after the deblocking treatment according to a first preset amplification factor by a preset super-resolution algorithm;
after amplifying the video frame to be repaired after the deblocking processing, if the sharpening degree of the video frame to be repaired after the amplifying processing is smaller than a preset sharpening degree threshold value, sharpening the video frame to be repaired after the amplifying processing through a preset sharpening algorithm;
after the video frame to be repaired after the amplification treatment is sharpened, if the noise value in the video frame to be repaired after the sharpening treatment is greater than a preset noise threshold value, the noise reduction treatment is carried out on the video frame to be repaired after the sharpening treatment through a preset noise reduction algorithm.
Optionally, the repair module 930 is configured to:
amplifying the video frame to be repaired according to a second preset amplification factor by a preset super-resolution algorithm;
after the video frame to be repaired is amplified, performing deblocking processing on the amplified video frame to be repaired by a preset deblocking algorithm;
after performing deblocking processing on the video frame to be repaired after the amplification processing, if the sharpening degree of the video frame to be repaired after the deblocking processing is smaller than a preset sharpening degree threshold value, performing sharpening processing on the video frame to be repaired after the deblocking processing through a preset sharpening algorithm;
after sharpening the video frame to be repaired after the deblocking processing, if the noise value in the video frame to be repaired after the sharpening processing is greater than a preset noise threshold value, carrying out noise reduction processing on the video frame to be repaired after the sharpening processing through a preset noise reduction algorithm.
Optionally, the video format of the video to which the video frame to be repaired belongs is YUV format.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
In the embodiment of the disclosure, any video frame to be repaired can be repaired, and the image quality of the repaired video frame is improved compared with that of the video frame before repair. Meanwhile, the embodiment of the disclosure can distinguish the video frames to be repaired based on the image quality damage degree of different video frames to be repaired, if the image quality damage degree is higher, the video frames to be repaired are seriously damaged video frames, and if the image quality damage degree is lower, the video frames to be repaired are slightly damaged video frames. After distinguishing the video frames to be repaired, the video frames to be repaired can be repaired through at least one repair algorithm according to different repair sequences, the repair treatment is more targeted, and the obtained repaired video frames have higher image quality.
It should be noted that: in the video restoration device provided in the above embodiment, only the division of the above functional modules is used for illustration, and in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules, so as to perform all or part of the functions described above. In addition, the apparatus for repairing video and the method embodiment for repairing video provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the apparatus for repairing video and the method embodiment are detailed in the method embodiment, and are not repeated here.
Fig. 10 shows a schematic structural diagram of a computer device 1900 provided in an exemplary embodiment of the present disclosure. The computer device 1900 may vary considerably in configuration or performance and may include one or more processors (central processing units, CPU) 1910 and one or more memories 1920. Wherein the memory 1920 stores at least one instruction that is loaded and executed by the processor 1910 to implement the method for repairing video described in the above embodiments.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A method of repairing video, the method comprising:
obtaining a video frame to be repaired;
determining the image quality damage degree of the video frame to be repaired;
if the image quality damage degree of the video frame to be repaired is larger than or equal to a preset damage degree threshold value, performing deblocking processing on the video frame to be repaired through a preset deblocking algorithm;
after the video frame to be repaired is subjected to deblocking treatment, amplifying the video frame to be repaired after the deblocking treatment according to a first preset amplification factor by a preset super-resolution algorithm;
after amplifying the video frame to be repaired after the deblocking processing, if the sharpening degree of the video frame to be repaired after the amplifying processing is smaller than a preset sharpening degree threshold value, sharpening the video frame to be repaired after the amplifying processing through a preset sharpening algorithm;
after the video frame to be repaired after the amplification treatment is sharpened, if the noise value in the video frame to be repaired after the sharpening treatment is greater than a preset noise threshold value, carrying out noise reduction treatment on the video frame to be repaired after the sharpening treatment through a preset noise reduction algorithm;
And if the image quality damage degree of the video frame to be repaired is smaller than the preset damage degree threshold, performing second repair processing on the video frame to be repaired through at least one repair algorithm according to the light damage repair sequence.
2. The method of claim 1, wherein the determining the image quality impairment of the video frame to be repaired comprises:
determining at least one image quality impairment algorithm;
calculating the image quality damage degree of the video frame to be repaired through each image quality damage degree algorithm respectively to obtain sub-image quality damage degrees corresponding to each image quality damage degree algorithm respectively;
and carrying out weighted summation on the quality impairment degree of each sub-image to obtain the quality impairment degree of the video frame to be repaired.
3. The method of claim 1, wherein said performing a second repair process on said video frame to be repaired by at least one repair algorithm in a light damage repair order comprises:
amplifying the video frame to be repaired according to a second preset amplification factor by a preset super-resolution algorithm;
after the video frame to be repaired is amplified, performing deblocking processing on the amplified video frame to be repaired by a preset deblocking algorithm;
After performing deblocking processing on the video frame to be repaired after the amplification processing, if the sharpening degree of the video frame to be repaired after the deblocking processing is smaller than a preset sharpening degree threshold value, performing sharpening processing on the video frame to be repaired after the deblocking processing through a preset sharpening algorithm;
after sharpening the video frame to be repaired after the deblocking processing, if the noise value in the video frame to be repaired after the sharpening processing is greater than a preset noise threshold value, carrying out noise reduction processing on the video frame to be repaired after the sharpening processing through a preset noise reduction algorithm.
4. A method according to any one of claims 1-3, wherein the video format of the video to which the video frame to be repaired belongs is YUV format.
5. An apparatus for repairing video, the apparatus comprising:
the acquisition module is used for acquiring the video frame to be repaired;
the determining module is used for determining the image quality damage degree of the video frame to be repaired;
the restoration module is used for carrying out deblocking effect processing on the video frame to be restored through a preset deblocking effect algorithm when the image quality damage degree of the video frame to be restored is greater than or equal to a preset damage degree threshold value; after the video frame to be repaired is subjected to deblocking treatment, amplifying the video frame to be repaired after the deblocking treatment according to a first preset amplification factor by a preset super-resolution algorithm; after amplifying the video frame to be repaired after the deblocking processing, if the sharpening degree of the video frame to be repaired after the amplifying processing is smaller than a preset sharpening degree threshold value, sharpening the video frame to be repaired after the amplifying processing through a preset sharpening algorithm; after the video frame to be repaired after the amplification treatment is sharpened, if the noise value in the video frame to be repaired after the sharpening treatment is greater than a preset noise threshold value, carrying out noise reduction treatment on the video frame to be repaired after the sharpening treatment through a preset noise reduction algorithm; and when the image quality damage degree of the video frame to be repaired is smaller than the preset damage degree threshold, performing second repair processing on the video frame to be repaired through at least one repair algorithm according to the light damage repair sequence.
6. The apparatus of claim 5, wherein the means for determining is configured to:
determining at least one image quality impairment algorithm;
calculating the image quality damage degree of the video frame to be repaired through each image quality damage degree algorithm respectively to obtain sub-image quality damage degrees corresponding to each image quality damage degree algorithm respectively;
and carrying out weighted summation on the quality impairment degree of each sub-image to obtain the quality impairment degree of the video frame to be repaired.
7. The apparatus of claim 5, wherein the repair module is configured to:
amplifying the video frame to be repaired according to a second preset amplification factor by a preset super-resolution algorithm;
after the video frame to be repaired is amplified, performing deblocking processing on the amplified video frame to be repaired by a preset deblocking algorithm;
after performing deblocking processing on the video frame to be repaired after the amplification processing, if the sharpening degree of the video frame to be repaired after the deblocking processing is smaller than a preset sharpening degree threshold value, performing sharpening processing on the video frame to be repaired after the deblocking processing through a preset sharpening algorithm;
After sharpening the video frame to be repaired after the deblocking processing, if the noise value in the video frame to be repaired after the sharpening processing is greater than a preset noise threshold value, carrying out noise reduction processing on the video frame to be repaired after the sharpening processing through a preset noise reduction algorithm.
8. The apparatus according to any one of claims 5-7, wherein the video format of the video to which the video frame to be repaired belongs is YUV format.
9. A computer device comprising a processor, a communication interface, a memory, and a communication bus, wherein:
the processor, the communication interface and the memory complete communication with each other through the communication bus;
the memory is used for storing a computer program;
the processor is configured to execute a program stored on the memory to implement the method steps of any one of claims 1-4.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910692753.6A CN110378860B (en) | 2019-07-30 | 2019-07-30 | Method, device, computer equipment and storage medium for repairing video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910692753.6A CN110378860B (en) | 2019-07-30 | 2019-07-30 | Method, device, computer equipment and storage medium for repairing video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110378860A CN110378860A (en) | 2019-10-25 |
| CN110378860B true CN110378860B (en) | 2023-08-18 |
Family
ID=68256921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910692753.6A Active CN110378860B (en) | 2019-07-30 | 2019-07-30 | Method, device, computer equipment and storage medium for repairing video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110378860B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113507625B (en) * | 2021-06-22 | 2022-08-19 | 西安理工大学 | Self-adaptive video restoration method |
| CN114501139A (en) * | 2022-03-31 | 2022-05-13 | 深圳思谋信息科技有限公司 | Video processing method and device, computer equipment and storage medium |
| CN115082357B (en) * | 2022-07-20 | 2022-11-25 | 深圳思谋信息科技有限公司 | Video denoising data set generation method and device, computer equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102231790A (en) * | 2011-06-23 | 2011-11-02 | 上海大学 | Method for restoring scratches of video sequence |
| EP2482558A1 (en) * | 2009-11-03 | 2012-08-01 | Huawei Technologies Co., Ltd. | Method, apparatus and system for evaluation of video quality |
| CN105809639A (en) * | 2016-03-03 | 2016-07-27 | 上海大学 | Restoration method for color fading and flashing in old films |
| CN206249426U (en) * | 2016-09-30 | 2017-06-13 | 宁波市东望智能***工程有限公司 | A kind of image restoration system |
| CN108961186A (en) * | 2018-06-29 | 2018-12-07 | 赵岩 | A kind of old film reparation recasting method based on deep learning |
| CN109660821A (en) * | 2018-11-27 | 2019-04-19 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and storage medium |
| CN109887515A (en) * | 2019-01-29 | 2019-06-14 | 北京市商汤科技开发有限公司 | Audio-frequency processing method and device, electronic equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI488143B (en) * | 2009-12-02 | 2015-06-11 | Acer Inc | Method for repairing image |
-
2019
- 2019-07-30 CN CN201910692753.6A patent/CN110378860B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2482558A1 (en) * | 2009-11-03 | 2012-08-01 | Huawei Technologies Co., Ltd. | Method, apparatus and system for evaluation of video quality |
| CN102231790A (en) * | 2011-06-23 | 2011-11-02 | 上海大学 | Method for restoring scratches of video sequence |
| CN105809639A (en) * | 2016-03-03 | 2016-07-27 | 上海大学 | Restoration method for color fading and flashing in old films |
| CN206249426U (en) * | 2016-09-30 | 2017-06-13 | 宁波市东望智能***工程有限公司 | A kind of image restoration system |
| CN108961186A (en) * | 2018-06-29 | 2018-12-07 | 赵岩 | A kind of old film reparation recasting method based on deep learning |
| CN109660821A (en) * | 2018-11-27 | 2019-04-19 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and storage medium |
| CN109887515A (en) * | 2019-01-29 | 2019-06-14 | 北京市商汤科技开发有限公司 | Audio-frequency processing method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 数字图像修复技术在缺损照片处理中的应用探讨;丁丰;;科技创新与应用(32);107页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110378860A (en) | 2019-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110378860B (en) | Method, device, computer equipment and storage medium for repairing video | |
| WO2016206087A1 (en) | Low-illumination image processing method and device | |
| CN109743473A (en) | Video image 3 D noise-reduction method, computer installation and computer readable storage medium | |
| KR102182697B1 (en) | Apparatus and method for processing image | |
| CN113099067B (en) | Reversible information hiding method and system based on pixel value sequencing prediction and diamond prediction | |
| CN113450290A (en) | Low-illumination image enhancement method and system based on image inpainting technology | |
| CN111445424A (en) | Image processing method, image processing device, mobile terminal video processing method, mobile terminal video processing device, mobile terminal video processing equipment and mobile terminal video processing medium | |
| US11948278B2 (en) | Image quality improvement method and image processing apparatus using the same | |
| Wang et al. | Gif2video: Color dequantization and temporal interpolation of gif images | |
| CN111429357A (en) | Training data determination method, video processing method, device, equipment and medium | |
| CN107301662A (en) | Compression restoration methods, device, equipment and the storage medium of depth image | |
| CN109949234A (en) | Video restoration model training method and video restoration method based on depth network | |
| CN115115540A (en) | Unsupervised low-light image enhancement method and unsupervised low-light image enhancement device based on illumination information guidance | |
| CN113612996A (en) | Video denoising method and device based on time domain filtering | |
| CN113012061A (en) | Noise reduction processing method and device and electronic equipment | |
| CN117333398A (en) | Multi-scale image denoising method and device based on self-supervision | |
| CN115131229A (en) | Image noise reduction and filtering data processing method and device and computer equipment | |
| CN114119383A (en) | Underwater image restoration method based on multi-feature fusion | |
| US20210090204A1 (en) | Method and system for data processing | |
| Jiang et al. | Haze relevant feature attention network for single image dehazing | |
| CN115311161B (en) | Image enhancement method, device, equipment and storage medium based on artificial intelligence | |
| CN114584831B (en) | Video optimization processing method, device, equipment and storage medium for improving video definition | |
| CN107509074B (en) | Self-adaptive 3D video compression coding and decoding method based on compressed sensing | |
| EP3070669A1 (en) | Method and apparatus for color smoothing in an alpha matting process | |
| CN112533024A (en) | Face video processing method and device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |