Image quality enhancement method, device, equipment, medium and product

Abstract

The invention discloses an image quality enhancement method and device, equipment, a medium and a product, which are applied to the technical field of video coding and decoding, and the method comprises the steps: parsing code stream data, and obtaining the distance between a reconstruction frame and a previous instant decoding refresh frame and the hierarchy of a pyramid reference frame structure; determining a weight coefficient corresponding to the reconstructed frame based on the distance and the hierarchy; wherein the weight coefficient is in positive correlation with the hierarchy and the distance; calculating an enhancement strength factor corresponding to the reconstructed frame based on the weight coefficient; and performing image quality enhancement on the reconstructed frame based on the enhancement intensity factor. Therefore, the image quality fluctuation can be reduced, the image quality enhancement effect is improved, and the user experience is further improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of video coding, in particular to a picture quality enhancement method and device, equipment, medium and product. BACKGROUND

[0002] At present, quantization in the video coding process will introduce compression distortion, and after decoding at the playback end, image picture quality enhancement technology will be used to enhance the picture quality, but the existing picture quality enhancement method is usually global, which causes the frame with good picture quality to become better after enhancement, while the frame with poor picture quality still has a gap with the frame with good picture quality, and even enlarges the gap, aggravates the picture quality fluctuation, and affects the user experience.

[0003] Therefore, how to reduce the picture quality fluctuation, improve the picture quality enhancement effect, and further improve the user experience is a technical problem to be solved at present. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a picture quality enhancement method, device, equipment, medium and product, which can reduce the picture quality fluctuation, improve the picture quality enhancement effect, and further improve the user experience.

[0005] In a first aspect, the present application provides a picture quality enhancement method, comprising: parsing code stream data to obtain a distance between a reconstructed frame and a previous instant decoding refresh frame and a level of a pyramid reference frame structure; determining a weight coefficient corresponding to the reconstructed frame based on the distance and the level; wherein the weight coefficient is positively correlated with the level and the distance; calculating an enhancement intensity factor corresponding to the reconstructed frame based on the weight coefficient; and performing picture quality enhancement on the reconstructed frame based on the enhancement intensity factor.

[0006] Optionally, determining the weight coefficient corresponding to the reconstructed frame based on the distance and the level comprises: determining the weight coefficient corresponding to the reconstructed frame based on a first adjustment coefficient corresponding to the distance and the distance, and a second adjustment coefficient corresponding to the level and the level.

[0007] Optionally, determining the weight coefficient corresponding to the reconstructed frame based on the distance and the level comprises: using a preset weight coefficient calculation formula, and determining the weight coefficient corresponding to the reconstructed frame based on a first adjustment coefficient corresponding to the distance and the distance, and a second adjustment coefficient corresponding to the level and the level, the preset weight coefficient calculation formula is: ; wherein W represents the weight coefficient, L represents the level, D represents the distance, a represents the first adjustment coefficient, and β represents the second adjustment coefficient.

[0008] Optionally, the calculation of the enhancement intensity factor corresponding to the reconstructed frame based on the weight coefficient comprises: calculating a basic enhancement factor based on the weight coefficient; and determining the enhancement intensity factor corresponding to the reconstructed frame based on the basic enhancement factor and a third adjustment coefficient.

[0009] Optionally, the calculation of the basic enhancement factor based on the weight coefficient comprises: calculating the basic enhancement factor based on the weight coefficient and a preset basic enhancement factor calculation formula, the basic enhancement factor calculation formula being: ; wherein, represents the basic enhancement factor, and W represents the weight coefficient.

[0010] Optionally, the determination of the enhancement intensity factor corresponding to the reconstructed frame based on the basic enhancement factor and the third adjustment coefficient comprises: determining the third adjustment coefficient based on the frame type of the reconstructed frame; and determining the enhancement intensity factor corresponding to the reconstructed frame based on the basic enhancement factor and the third adjustment coefficient.

[0011] In a second aspect, the present application provides a picture quality enhancement device, comprising: a bitstream data analysis module configured to analyze bitstream data to obtain a distance between a reconstructed frame and a previous instant decoding refresh frame and a level of a pyramid reference frame structure; a weight coefficient determination module configured to determine a weight coefficient corresponding to the reconstructed frame based on the distance and the level; wherein the weight coefficient is positively correlated with the level and the distance; an intensity factor calculation module configured to calculate an enhancement intensity factor corresponding to the reconstructed frame based on the weight coefficient; a picture quality enhancement module configured to perform picture quality enhancement on the reconstructed frame based on the enhancement intensity factor.

[0012] In a third aspect, the present application provides an electronic device comprising a memory and a processor, wherein: the memory is configured to save a computer program; and the processor is configured to execute the computer program to implement the picture quality enhancement method described above.

[0013] In a fourth aspect, the present application provides a computer readable storage medium configured to save a computer program, wherein the computer program is executed by a processor to implement the picture quality enhancement method described above.

[0014] In a fifth aspect, the present application provides a computer program product comprising computer programs / instructions, which are executed by a processor to implement the steps of the picture quality enhancement method described above.

[0015] It can be known from the above scheme that the picture quality enhancement method provided by the application comprises: analyzing code stream data to obtain a distance between a reconstructed frame and a previous instant decoding refresh frame and a level in a pyramid reference frame structure; determining a weight coefficient corresponding to the reconstructed frame based on the distance and the level; wherein the weight coefficient is positively correlated with the level and the distance; calculating an enhancement intensity factor corresponding to the reconstructed frame based on the weight coefficient; and performing picture quality enhancement on the reconstructed frame based on the enhancement intensity factor.

[0016] It can be seen that the beneficial effects of the application are: the enhancement intensity factor corresponding to the reconstructed frame is calculated by the weight coefficient, and the weight coefficient is calculated according to the distance between the reconstructed frame and the previous instant decoding refresh frame and the level in the pyramid reference frame structure, and the weight coefficient is positively correlated with the distance between the reconstructed frame and the previous instant decoding refresh frame and the level in the pyramid reference frame structure, that is, the greater the distance, the greater the weight coefficient, the higher the level, and the greater the weight coefficient, so that considering that the higher the level in the pyramid reference frame structure, the greater the distortion of the reference frame itself is accumulated and propagated multiple times, and the distortion is greater, and as the frame moves away from the instant decoding refresh frame, the prediction link becomes longer, and the accumulated distortion gradually increases, the weight coefficient is determined according to the level and the distance from the instant decoding refresh frame, and then the weight coefficient is used to realize the differential enhancement of the reconstructed frame, which can reduce the picture quality fluctuation, improve the picture quality enhancement effect, and further improve the user experience.

[0017] Correspondingly, the picture quality enhancement device, equipment, readable storage medium and product provided by the application also have the above technical effects. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only embodiments of the application, and those skilled in the art can obtain other drawings according to the provided drawings without creating any creative labor.

[0019] Figure 1 A pyramid reference frame structure schematic diagram provided by the embodiment of the application; Figure 2 An IDR frame structure schematic diagram provided by the embodiment of the application; Figure 3 A picture quality enhancement method flowchart provided by the embodiment of the application; Figure 4 A picture quality enhancement schematic diagram provided by the embodiment of the application; Figure 5 A picture quality enhancement flowchart provided by the embodiment of the application; Figure 6 A picture quality adjustment process schematic diagram provided for an embodiment of the present application; Figure 7 A picture quality enhancement device structure schematic diagram provided for an embodiment of the present application; Figure 8 An electronic device structure diagram provided for an embodiment of the present application. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0021] Quantization in a video encoding process can introduce compression distortion (block effect, blur, color distortion, etc.), and video encoding usually adopts a pyramid reference frame structure to utilize the temporal redundancy between frames for prediction compression. High-level frames are predicted and encoded by referring to low-level frames (I frames or P frames or B frames), as shown in Figure 1 . Figure 1 A pyramid reference frame structure schematic diagram provided for an embodiment of the present application, which can cause accumulation and propagation of compression distortion. In addition, a common strategy of an encoder is to allocate more code rate (use a lower quantization parameter QP) for low-level frames to guarantee quality, and relatively less code rate is allocated for middle-level and top-level frames (or the encoder uses a higher QP to compress them). These factors superimpose each other, and as the reference level becomes deeper, the distortion of the reference frames relied on by the frames has been accumulated and propagated for multiple times, the distortion is relatively large, and the image quality will also become poor. Figure 1 The middle t0 is the bottom layer of the pyramid.

[0022] In addition, in addition to the influence of the reference frame pyramid structure, the reference distance of the encoded frame from the IDR frame is also an important factor. As the distance from the IDR (instantaneous decoding refresh frame) increases, the prediction link becomes longer, the accumulated distortion gradually increases, the picture detail blurs, the block effect increases, and the picture quality gradually deteriorates. When the next IDR frame is reached, as shown in Figure 2 . Figure 2 An IDR frame structure schematic diagram provided for an embodiment of the present application. The encoder resets the prediction chain, and all previous accumulated distortion is completely removed, the picture becomes clear instantly, and the picture quality will appear fluctuations from good to bad and then to good. The visual performance of such quality periodic fluctuations is usually called breathing effect.

[0023] Considering the influence of the above factors, the quality of the encoded video received by the playback end fluctuates, the consistency of the video quality of the playback end is difficult to guarantee, and the user experience is affected.

[0024] On the other hand, some image quality enhancement technologies of the playback end can greatly help to improve the image quality, but the image quality optimization is usually global and does not take into account the quality fluctuation caused by encoding, so that the enhanced frames with good quality become better, while the frames with poor quality still have a gap with the frames with good quality, and even the gap is enlarged, which aggravates the quality fluctuation and affects the user experience.

[0025] Therefore, the reference structure information of the encoding end is converted into the enhancement decision basis of the playback end in the present application, the breathing effect elimination and quality smooth transition are realized through quantization of level sensitivity and distance decay effect, the technical closed loop of structure perception and dynamic enhancement is established, and the image quality experience of the user watching the video at the playback end is improved.

[0026] Referring to Figure 3 The embodiment of the present application discloses an image quality enhancement method, which comprises the following steps: Step S11: Analyzing the code stream data to obtain the distance between the reconstructed frame and the previous instant decoding refresh frame and the level in the pyramid reference frame structure.

[0027] In the embodiment of the present application, the code stream data can be analyzed to extract metadata, and the distance between the reconstructed frame and the previous instant decoding refresh frame and the level in the pyramid reference frame structure are calculated based on the metadata. The extracted metadata is reference relationship metadata, including POC (picture order count), GOP size (picture group size), and frame type, and the frame type can include I frame, P frame, and B frame.

[0028] The calculation formula of the level of the reconstructed frame in the pyramid reference frame structure is: ; Wherein, N is the GOP size, p is the relative position of the current frame, i.e., the current reconstructed frame, in the GOP (picture group), p = poc mod N, gcd(p, N) represents the greatest common divisor of p and N, and log2 is the logarithmic function with 2 as the base.

[0029] The calculation formula of the distance between the reconstructed frame and the previous instant decoding refresh frame is: . Wherein, poc is the POC value of the current frame, : the POC value of the previous IDR frame (i.e., the previous instant decoding refresh frame) closest to the current frame.

[0030] Step S12: determining a weight coefficient corresponding to the reconstructed frame based on the distance and the level; wherein the weight coefficient is positively correlated with the level and the distance.

[0031] The embodiment of the present application can determine the weight coefficient corresponding to the reconstructed frame based on the first adjustment coefficient corresponding to the distance and the distance, and the second adjustment coefficient corresponding to the level and the level.

[0032] In an optional implementation, the weight coefficient corresponding to the reconstructed frame is determined based on the first adjustment coefficient corresponding to the distance and the distance, and the second adjustment coefficient corresponding to the level and the level, by using a preset weight coefficient calculation formula. ; wherein W represents the weight coefficient, L represents the level, D represents the distance, a represents the first adjustment coefficient, and b represents the second adjustment coefficient. The level range is an integer [0, 5], D is a non-negative integer, 0≤a, b≤1 and a+b=1.

[0033] Step S13: calculating an enhancement intensity factor corresponding to the reconstructed frame based on the weight coefficient.

[0034] The embodiment of the present application can calculate a basic enhancement factor based on the weight coefficient; and determine the enhancement intensity factor corresponding to the reconstructed frame based on the basic enhancement factor and a third adjustment coefficient.

[0035] In an optional implementation, the basic enhancement factor is calculated based on the weight coefficient, including: calculating the basic enhancement factor based on the weight coefficient and a preset basic enhancement factor calculation formula. ; wherein, represents the basic enhancement factor, and W represents the weight coefficient.

[0036] It should be noted that the influence of the pyramid level (L) and the distance (D) from the IDR frame on the picture quality decay is nonlinear, the picture quality decay of the low L layer is slower, and the picture quality decay of the high L layer is faster; when close to the IDR frame (D is small), the quality is relatively stable, and the quality deteriorates rapidly after the distance increases. Therefore, the embodiment of the present application designs a picture quality enhancement intensity control factor, i.e., a basic enhancement factor, to ensure that the enhanced picture quality is in a relatively stable state. W is divided into three intervals, W<0.3 is a protection interval, 0.3≤W≤0.7 is a balance interval, and W>0.7 is an enhancement interval. ∈[0.05,1.0].

[0037] In an optional embodiment, the enhancement intensity factor corresponding to the reconstructed frame is determined based on the base enhancement factor and a third adjustment coefficient, including: determining the third adjustment coefficient based on the frame type of the reconstructed frame; and determining the enhancement intensity factor corresponding to the reconstructed frame based on the base enhancement factor and the third adjustment coefficient. In the embodiments of the present application, the third adjustment coefficient corresponding to an I frame is smaller than the third adjustment coefficient corresponding to a P frame, which is smaller than the third adjustment coefficient corresponding to a B frame. For example, the third adjustment coefficient corresponding to an I frame is 0.8, the third adjustment coefficient corresponding to a P frame is 1.0, and the third adjustment coefficient corresponding to a B frame is 1.2. The calculation formula of the enhancement intensity factor is: ; wherein S is the enhancement intensity factor, is the third adjustment coefficient, and S ∈ [0.04, 1.2].

[0038] Step S14: performing quality enhancement on the reconstructed frame based on the enhancement intensity factor.

[0039] The enhancement intensity factor represents the intensity of quality enhancement, and the greater the enhancement intensity factor, the greater the intensity of quality enhancement. The enhancement intensity factor can be transmitted to a preset image enhancement algorithm in the embodiments of the present application to achieve quality enhancement.

[0040] It can be seen that the embodiments of the present application calculate the enhancement intensity factor corresponding to the reconstructed frame through the weight coefficient, the weight coefficient is calculated according to the distance between the reconstructed frame and the previous instant decoding refresh frame and the level in the pyramid reference frame structure, and the weight coefficient and the distance between the reconstructed frame and the previous instant decoding refresh frame and the level in the pyramid reference frame structure are positively correlated, that is, the greater the distance, the greater the weight coefficient, and the higher the level, the greater the weight coefficient. Therefore, considering that the distortion of the reference frame relied on by the frame in the pyramid reference frame structure is accumulated and propagated for multiple times, the distortion is greater, and as the frame moves away from the instant decoding refresh frame, the prediction link becomes longer, and the accumulated distortion gradually increases, the weight coefficient is determined according to the level and the distance from the instant decoding refresh frame, and then the weight coefficient is used to realize the differentiated enhancement of the reconstructed frame, which can reduce the quality fluctuation, improve the quality enhancement effect, and further improve the user experience.

[0041] Referring to Figure 4As shown, the embodiment of the present application provides a picture quality enhancement schematic diagram. The video code stream is parsed, the weight is calculated, the dynamic picture quality enhancement is performed, and then the consistent picture output is performed. In the code stream parsing, the reference relationship metadata in the video stream is extracted during decoding, including the frame type, the reference frame list, and the like, so that the reference dependence between the reconstructed frames and the distance between the reconstructed frames and the previous IDR frame are obtained. In the weight calculation, the key weight coefficient of the frame is calculated based on a preset weight coefficient calculation formula, and the quality attenuation degree is quantified. In the dynamic picture quality enhancement, the picture quality enhancement strength of different intensities is performed according to the reconstructed frame type and the calculated weight coefficient, so that the fluctuation of the output picture quality is small.

[0042] In the code stream parsing process, the frame type (I frame / P frame / B frame) of each reconstructed frame, the reference frame pyramid level L where the frame is located, and the distance D of the current frame from the previous nearest IDR frame are mainly parsed. The pyramid level L where the current frame is located is calculated, and the calculation formula is as follows: ; Wherein: N is the GOP size, p is the relative position of the current frame in the GOP, p = poc mod N, gcd(p, N) represents the greatest common divisor of p and N, and log2 is the logarithmic function with 2 as the base. The distance D of the current frame from the previous nearest IDR frame is calculated by the following formula: ; wherein: poc is the POC value of the current frame, is the POC value of the previous IDR frame closest to the current frame.

[0043] Further, referring to Figure 5 As shown, the embodiment of the present application provides a picture quality enhancement flowchart, Figure 5 which shows the weight calculation and dynamic picture quality enhancement control process for the current frame to be processed. The key weight calculation is based on the pyramid level (L) and the frame weight calculation process of the IDR distance (D) as follows: ; Wherein, L is the pyramid level, the range is an integer [0, 5]. D is the distance from the nearest IDR frame, which is a non-negative integer, α, β are adjustment coefficients (0≤α, β≤1 and α+β=1).

[0044] Further, dynamic enhancement control, the influence of pyramid level (L) and distance (D) from IDR frame on picture quality degradation is nonlinear, picture quality degradation of low L layer is slower, and picture quality degradation of high L layer is faster; when close to IDR frame (D is small), the quality is relatively stable, and the quality deteriorates rapidly after the distance increases. Considering this feature, an embodiment of the present application designs a picture quality enhancement intensity control factor to ensure that the enhanced picture quality is in a relatively stable state.

[0045] ; W is divided into three intervals, W<0.3 is a protection interval, 0.3≤W≤0.7 is a balance interval, and W>0.7 is an enhancement interval. .

[0046] Adjusting coefficient according to frame type The adjusting coefficient of I frame is 0.8, the adjusting coefficient of P frame is 1.0, and the adjusting coefficient of B frame is 1.2. The final enhancement intensity factor . Wherein, S∈[0.04, 1.2], the final enhancement emphasis factor is transmitted to the image enhancement algorithm to realize the adjustment of the picture quality. Referring to Figure 6 , Figure 6 is a picture quality adjustment process schematic diagram provided by an embodiment of the present application. For the frame to be processed, the enhancement intensity factor is calculated, the picture quality enhancement algorithm is called, and the rendering display is performed.

[0047] An embodiment of the present application combines video encoding reference structure information to enhance picture quality, fully considers the prediction dependence factors caused by the video encoding reference frame structure, and effectively solves the picture quality fluctuation problem caused by reference frame dependence. The reference pyramid structure information (level depth L, IDR distance D) of video encoding is converted into the enhancement decision basis of the playback end, breaking the blindness of the traditional algorithm global enhancement, and realizing the coding and decoding collaborative optimization. The influence of pyramid structure information (level depth L, IDR frame distance D) on propagation distortion is mathematically modeled, the distortion is quantifiable, and the weight factor used to control the intensity of picture quality enhancement is calculated. In the process of dynamic enhancement control of picture quality, in addition to considering the frame structure information, the frame type information is also considered. The dynamic control of the playback end picture quality enhancement is realized. This dynamic control compared with the enhancement of the global uniform intensity, helps to reduce the overall complexity and reduce the power consumption of the end side.

[0048] Thus, the problem of quality fluctuation of video frames at different levels caused by the pyramid structure of video encoding and the problem of quality decay caused by the lengthening of the reference link distance from the IDR frame, and the problem of periodic quality fluctuation (breathing effect) are solved. The traditional playback end enhancement algorithm ignores the level difference of the reference frame, resulting in the double defects of over-processing of low-level frames and insufficient compensation of high-level frames, which expands the quality fluctuation and affects the user experience. The embodiments of the present application can break the information fragmentation dilemma of encoding and playback quality optimization, obtain the reference relationship metadata (such as frame type, reference level depth, and distance from IDR frame) by analysis, and construct a quantitative driving adaptive enhancement model. Based on the dynamic regulation of the key weight of the reference level processing intensity: strengthen the noise reduction and blocking effect of high-level / distant frames, and suppress the over-enhancement of low-level / near frames, so as to realize distortion-oriented repair and quality smooth transition at the playback end, completely eliminate the breathing effect, and achieve the collaborative closed loop of encoding structure perception and accurate compensation at the playback end.

[0049] Referring to Figure 7 As shown in the figure, the present application provides a quality enhancement device, comprising: A code stream data analysis module 11 is configured to analyze the code stream data to obtain the distance between the reconstructed frame and the previous IDR frame and the level of the pyramid reference frame structure.

[0050] A weight coefficient determination module 12 is configured to determine the weight coefficient corresponding to the reconstructed frame based on the distance and the level. The weight coefficient is positively correlated with the level and the distance.

[0051] An intensity factor calculation module 13 is configured to calculate the enhancement intensity factor corresponding to the reconstructed frame based on the weight coefficient.

[0052] A quality enhancement module 14 is configured to perform quality enhancement on the reconstructed frame based on the enhancement intensity factor.

[0053] In an optional embodiment, the weight coefficient determination module 12 is specifically configured to determine the weight coefficient corresponding to the reconstructed frame based on a first adjustment coefficient corresponding to the distance and a second adjustment coefficient corresponding to the distance and the level.

[0054] In an optional embodiment, the weight coefficient determination module 12 is specifically configured to determine the weight coefficient corresponding to the reconstructed frame based on a first adjustment coefficient corresponding to the distance and a second adjustment coefficient corresponding to the distance and the level by using a preset weight coefficient calculation formula. ; Wherein, W represents the weight coefficient, L represents the level, D represents the distance, a represents the first adjustment coefficient, and b represents the second adjustment coefficient.

[0055] In an optional implementation, the intensity factor calculation module 13 can include:

[0056] a base enhancement factor calculation submodule configured to calculate a base enhancement factor based on the weight coefficient;

[0057] an enhancement intensity factor calculation submodule configured to determine an enhancement intensity factor corresponding to the reconstructed frame based on the base enhancement factor and a third adjustment coefficient.

[0058] In an optional implementation, the base enhancement factor calculation submodule is specifically configured to calculate the base enhancement factor based on the weight coefficient and a preset base enhancement factor calculation formula, and the base enhancement factor calculation formula is: ; Wherein, represents the base enhancement factor, and W represents the weight coefficient.

[0059] In an optional implementation, the enhancement intensity factor calculation submodule is specifically configured to determine the third adjustment coefficient based on a frame type of the reconstructed frame, and determine the enhancement intensity factor corresponding to the reconstructed frame based on the base enhancement factor and the third adjustment coefficient.

[0060] It can be seen that, in the embodiments of the present application, the enhancement intensity factor corresponding to the reconstructed frame is calculated based on the weight coefficient, the weight coefficient is calculated according to the distance between the reconstructed frame and the previous instant decoding refresh frame and the level in the pyramid reference frame structure, and the weight coefficient and the distance between the reconstructed frame and the previous instant decoding refresh frame and the level in the pyramid reference frame structure are positively correlated, that is, the greater the distance, the greater the weight coefficient, and the higher the level, the greater the weight coefficient. Therefore, considering that in the pyramid reference frame structure, the higher the level, the greater the distortion of the reference frame itself after multiple accumulations and propagations, and the greater the distortion, and as the frame moves away from the instant decoding refresh frame, the prediction link becomes longer, and the accumulated distortion gradually increases, the weight coefficient is determined according to the level and the distance from the instant decoding refresh frame, and then the weight coefficient is used to realize the differentiated enhancement of the reconstructed frame, which can reduce the quality fluctuation, improve the quality enhancement effect, and further improve the user experience.

[0061] Referring to Figure 8 As shown in the figure, the embodiments of the present application disclose an electronic device 20, which includes a processor 21 and a memory 22; wherein the memory 22 is used to save a computer program; the processor 21 is used to execute the computer program, and the quality enhancement method disclosed in the foregoing embodiments.

[0062] The specific process of the picture quality enhancement method can refer to the corresponding content disclosed in the foregoing embodiments, and will not be described here again.

[0063] The memory 22 can be a read-only memory, a random access memory, a magnetic disk, an optical disk, or the like, and can be temporarily stored or permanently stored.

[0064] In addition, the electronic device 20 further includes a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26; the power supply 23 is configured to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol followed by the communication interface 24 can be any communication protocol applicable to the technical solution of the present application, which will not be limited here; the input / output interface 25 is configured to obtain external input data or output data to the outside, and the specific interface type can be selected according to the specific application needs, which will not be limited here.

[0065] Further, the embodiment of the present application further discloses a computer readable storage medium for saving a computer program, wherein the computer program is executed by a processor to realize the picture quality enhancement method disclosed in the foregoing embodiment.

[0066] The specific process of the picture quality enhancement method can refer to the corresponding content disclosed in the foregoing embodiments, and will not be described here again.

[0067] Further, the embodiment of the present application further discloses a computer program product, including computer program / instructions, which are executed by a processor to realize the steps of the foregoing picture quality enhancement method.

[0068] The specific process of the picture quality enhancement method can refer to the corresponding content disclosed in the foregoing embodiments, and will not be described here again.

[0069] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts of each embodiment can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the related parts can be referred to the method part.

[0070] The steps of a method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module can reside in random access memory (RAM), flash memory, read-only memory (ROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, hard disk can be used for tangibly embodying the software module.

[0071] The above provides a quality enhancement method, device, equipment, medium and product, and the principles and implementation manners of the present application are described by applying specific examples. The above description of the embodiments is only used to help understand the method and its core idea; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range can be changed, and the above description should not be understood as a limitation of the present application.

Claims

1. An image quality enhancement method characterized by comprising: The method comprises the following steps: parsing the code stream data to obtain a distance between a reconstructed frame and a previous instant decoding refresh frame and a level in a pyramid reference frame structure; determining a weight coefficient corresponding to the reconstructed frame based on the distance and the level; wherein the weight coefficient is positively correlated with the level and the distance; calculating an enhancement intensity factor corresponding to the reconstructed frame based on the weight coefficient; performing quality enhancement on the reconstructed frame based on the enhancement intensity factor.

2. The image quality enhancement method of claim 1, wherein The method for determining the weight coefficient corresponding to the reconstructed frame based on the distance and the level comprises: determining the weight coefficient corresponding to the reconstructed frame based on a first adjustment coefficient corresponding to the distance and the distance, and a second adjustment coefficient corresponding to the level and the level.

3. The image quality enhancement method of claim 2, wherein The method for determining the weight coefficient corresponding to the reconstructed frame based on the distance and the level comprises: using a preset weight coefficient calculation formula, and determining the weight coefficient corresponding to the reconstructed frame based on a first adjustment coefficient corresponding to the distance and the distance, and a second adjustment coefficient corresponding to the level and the level, wherein the preset weight coefficient calculation formula is: ； wherein W represents the weight coefficient, L represents the level, D represents the distance, a represents the first adjustment coefficient, and b represents the second adjustment coefficient.

4. The picture quality enhancement method according to any one of claims 1 to 3, characterized by, The method for calculating the enhancement intensity factor corresponding to the reconstructed frame based on the weight coefficient comprises: calculating a basic enhancement factor based on the weight coefficient; determining the enhancement intensity factor corresponding to the reconstructed frame based on the basic enhancement factor and a third adjustment coefficient.

5. The method of claim 4, wherein The method for calculating the basic enhancement factor based on the weight coefficient comprises: calculating the basic enhancement factor based on the weight coefficient and a preset basic enhancement factor calculation formula, wherein the preset basic enhancement factor calculation formula is: ； wherein, denotes a base enhancement factor, W denotes a weight coefficient.

6. The method of claim 4, wherein The method for determining the enhancement intensity factor corresponding to the reconstructed frame based on the basic enhancement factor and the third adjustment coefficient comprises: determining the third adjustment coefficient based on a frame type of the reconstructed frame; determining the enhancement intensity factor corresponding to the reconstructed frame based on the basic enhancement factor and the third adjustment coefficient.

7. A device for enhancing image quality, characterized in that: The method comprises the following steps: a code stream data parsing module, configured to parse the code stream data to obtain a distance between a reconstructed frame and a previous instant decoding refresh frame and a level in a pyramid reference frame structure; a weight coefficient determining module, configured to determine a weight coefficient corresponding to the reconstructed frame based on the distance and the level; wherein the weight coefficient is positively correlated with the level and the distance; an intensity factor calculating module, configured to calculate an enhancement intensity factor corresponding to the reconstructed frame based on the weight coefficient; a quality enhancement module, configured to perform quality enhancement on the reconstructed frame based on the enhancement intensity factor.

8. An electronic device, comprising: The method comprises the following steps: a memory and a processor, wherein: the memory is configured to save a computer program; 9. A computer-readable storage medium, characterized in that, the processor is configured to execute the computer program to implement the quality enhancement method according to any one of claims 1 to 6. The computer program is saved, and when the computer program is executed by a processor, the quality enhancement method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instructions, when executed by the processor, implement the steps of the image quality enhancement method of any one of claims 1 to 6.

Images