Image preview method and device, electronic device and storage medium

Abstract

The present disclosure relates to an image preview method and apparatus, an electronic device, and a storage medium. The method comprises: obtaining target coded data, wherein the target coded data is obtained after a target coding network performs image encoding on a target image; and using a target preview network corresponding to the target coding network, performing image decoding on the target coded data to obtain a target preview image corresponding to the target image, wherein the resolution of the target preview image is lower than the resolution of the target image. Embodiments of the present disclosure can directly generate a target preview image with a lower resolution that effectively preserves the semantic information of the target image, thereby speeding up the generation of the target preview image and meeting user preview requirements.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to an image preview method and device, an electronic device, and a storage medium. Background Art

[0002] In recent years, end-to-end image coding technology based on deep learning has made rapid and in-depth progress. Some recently proposed technologies, such as JPEG, BPG, and VVC, have already reached or exceeded the encoding speed and compression ratio of traditional image coding technologies. Currently, end-to-end image coding technology has entered the standardization stage, and due to its superior performance, it is expected to be widely used in the future. In practical image coding applications, there is a need to preview the encoded data. Summary of the Invention

[0003] The present disclosure provides a technical solution for an image preview method and device, an electronic device, and a storage medium.

[0004] According to one aspect of the present disclosure, an image preview method is provided, comprising: obtaining target coded data, wherein the target coded data is obtained after a target coding network performs image encoding on a target image; and using a target preview network corresponding to the target coding network, performing image decoding on the target coded data to obtain a target preview image corresponding to the target image, wherein a resolution of the target preview image is smaller than a resolution of the target image.

[0005] In the disclosed embodiment, target coding data obtained after the target coding network performs image coding on the target image is obtained, and the target coding data is decoded using the target preview network corresponding to the target coding network, so that a target preview image with a lower resolution and better preservation of the semantic information of the target image can be directly generated, which can not only improve the generation speed of the target preview image, but also meet the preview needs of users.

[0006] In a possible implementation, the target coding data is obtained by sequentially entropy encoding K groups of target channel features corresponding to the target image; and using a target preview network corresponding to the target coding network to perform image decoding on the target coding data to obtain a target preview image corresponding to the target image includes: entropy decoding the target coding data to sequentially obtain the first to Nth groups of target channel features corresponding to the target image, where N<K; and using the target preview network to perform image decoding on the first to Nth groups of target channel features to obtain the target preview image.

[0007] Since the semantic information of the target image is concentrated in the bitstream data of the first several groups of target channel features that are entropy coded, only part of the bitstream data of the first N groups of target channel features that are entropy coded can be entropy decoded, and then only the first N groups of target channel features obtained by decoding can be used by the target preview network to perform image decoding. In this way, a target preview image with a small resolution that can better retain the original semantic information of the target image can be directly generated, which effectively improves the speed of generating the target preview image.

[0008] In a possible implementation, the target preview image includes N progressive target preview images; the target preview network is used to perform image decoding on the first to Nth groups of target channel features to obtain the target preview image, including: when the first to i-th groups of target channel features are decoded and the i+1-th to N-th groups of target channel features are not decoded, the entropy parameters of the i+1-th to N-th groups of target channel features are zero-filled to obtain the filling entropy parameters of the i+1-th to N-th groups of target channel features, where i≥1; the filling entropy parameters of the first to i-th groups of target channel features and the i+1-th to N-th groups of target channel features are input into the target preview network to obtain the i-th progressive target preview image.

[0009] Filling the entropy parameters of the undecoded target channel features with zero values can effectively reduce the time for determining the entropy parameters of the undecoded target channel features, thereby effectively increasing the generation speed of each progressive target preview image, reducing user waiting time, and improving user experience.

[0010] In a possible implementation, the method further includes: upsampling the target preview image to obtain a target decoded image corresponding to the target image, wherein the target decoded image has the same resolution as the target image.

[0011] The target preview image with a smaller resolution is upsampled to obtain a target decoded image with the target image resolution restored, thereby effectively meeting the user's need to view clear images with a larger resolution.

[0012] In one possible implementation, before using the target preview network to perform image decoding on the target coded data, the method further includes: using the target coding network to perform image encoding on a sample image to obtain sample coded data of the sample image; using an initial preview network to perform image decoding on the sample coded data to obtain a predicted preview image corresponding to the sample image, wherein a resolution of the predicted preview image is smaller than a resolution of the sample image; based on the predicted preview image, determining a predicted decoded image corresponding to the sample image; and using the sample image and the predicted decoded image to perform network training on the initial preview network to obtain the target preview network.

[0013] The target coding network is used to perform image coding on the sample image to obtain sample coding data of the sample image; the initial preview network is used to perform image decoding on the sample coding data to obtain a predicted preview image with a smaller resolution corresponding to the sample image; based on the predicted preview image, a predicted decoded image corresponding to the sample image is determined; the sample image and the predicted decoded image are used to perform network training on the initial preview network so that a trained target preview network can be obtained, and a preview image with a smaller resolution and better preservation of the original semantic information of the image is directly generated for the coding data of the target coding network, which can not only improve the generation speed of the preview image, but also meet the preview needs of users.

[0014] In a possible implementation, the sample coded data is obtained by sequentially performing entropy coding on K groups of sample channel features corresponding to the sample image; and using the initial preview network to perform image decoding on the sample coded data to obtain a predicted preview image corresponding to the sample image includes: performing entropy decoding on the sample coded data to obtain the first to Nth groups of sample channel features corresponding to the sample image; and using the initial preview network to perform image decoding on the first to Nth groups of sample channel features to obtain the predicted preview image.

[0015] Since the original semantic information of the sample image is concentrated in the code stream data of the first several groups of sample channel features that are entropy coded, only part of the code stream data of the first N groups of sample channel features that are entropy coded can be entropy decoded, and then only the first N groups of sample channel features obtained by decoding can be used by the initial preview network to perform image decoding. In this way, a prediction preview image with a small resolution that can better retain the original semantic information of the sample image can be directly generated, which effectively improves the speed of generating the prediction preview image.

[0016] In one possible implementation, the sample coded data includes code stream data corresponding to each group of sample channel features; the entropy decoding of the sample coded data to obtain the first to Nth groups of sample channel features corresponding to the sample image includes: determining an entropy parameter of the first group of sample channel features, and using the entropy parameter of the first group of sample channel features to perform entropy decoding on the code stream data corresponding to the first group of sample channel features to obtain the first group of sample channel features; when i>1, determining the entropy parameter of the i-th group of sample channel features based on the decoded first to i-1th groups of sample channel features, and using the entropy parameter of the i-th group of sample channel features to perform entropy decoding on the code stream data corresponding to the i-th group of sample channel features to obtain the i-th group of sample channel features.

[0017] When entropy decoding is performed on the 1st to Nth groups of sample channel features in sequence, except for the 1st group of sample channel features, any remaining i-th group of sample channel features uses the 1st to i-1th groups of sample channel features that have previously completed entropy decoding as context information, so as to accurately decode the 1st to Nth groups of sample channel features.

[0018] In a possible implementation, the predicted preview image includes N progressive predicted preview images; the using the initial preview network to perform image decoding on the first to Nth groups of sample channel features to obtain the predicted preview image includes: when the first to i-th groups of sample channel features are decoded and the i+1-th to N-th groups of sample channel features are not decoded, zero-filling the entropy parameters of the i+1-th to N-th groups of sample channel features to obtain filling entropy parameters of the i+1-th to N-th groups of sample channel features, where i≥1; inputting the filling entropy parameters of the first to i-th groups of sample channel features and the i+1-th to N-th groups of sample channel features into the initial preview network to obtain the i-th progressive predicted preview image.

[0019] Filling the entropy parameters of the undecoded sample channel features with zero values can effectively reduce the time for determining the entropy parameters of the undecoded sample channel features, thereby effectively increasing the generation speed of each progressive prediction preview image, reducing user waiting time, and improving user experience.

[0020] In a possible implementation, determining the predicted decoded image corresponding to the sample image based on the predicted preview image includes: upsampling the predicted preview image to obtain the predicted decoded image, wherein the predicted decoded image and the sample image have the same resolution.

[0021] Since the resolution of the predicted preview image is smaller than that of the original sample image, the predicted preview image is upsampled to obtain a predicted decoded image with the same resolution as the original sample image, so as to effectively carry out subsequent comparative training.

[0022] In one possible implementation, performing network training on the initial preview network using the sample image and the predicted decoded image to obtain the target preview network includes: determining a distortion rate of the predicted decoded image relative to the sample image; and performing network training on the initial preview network based on the distortion rate to obtain the target preview network.

[0023] After upsampling the predicted preview image output by the initial preview network to obtain a predicted decoded image, the distortion rate of the predicted decoded image relative to the sample image is determined. Based on the distortion rate, the initial preview network can be trained to optimize the network parameters of the initial preview network, thereby ultimately training the target preview network.

[0024] According to one aspect of the present disclosure, an image preview device is provided, comprising: an acquisition module for acquiring target coded data, wherein the target coded data is obtained after a target coding network performs image coding on a target image; and an image preview module for performing image decoding on the target coded data using a target preview network corresponding to the target coding network to obtain a target preview image corresponding to the target image, wherein a resolution of the target preview image is smaller than a resolution of the target image.

[0025] According to one aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to call the instructions stored in the memory to execute the above method.

[0026] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above method is implemented.

[0027] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, rather than limiting the present disclosure. Other features and aspects of the present disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure.

[0029] Figure 1A flowchart of an image preview method according to an embodiment of the present disclosure is shown;

[0030] Figure 2 A block diagram of an image preview device according to an embodiment of the present disclosure is shown;

[0031] Figure 3 A block diagram illustrating an electronic device according to an embodiment of the present disclosure is shown;

[0032] Figure 4 A block diagram of another electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0033] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0034] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0035] The term "and / or" herein simply describes an association relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can represent the existence of three situations: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0036] In addition, numerous specific details are provided in the following detailed description to better illustrate the present disclosure. Those skilled in the art will appreciate that the present disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art are not described in detail in order to highlight the main points of the present disclosure.

[0037] In recent years, end-to-end image coding technology based on deep learning has made rapid and in-depth progress. Some recently proposed technologies, such as JPEG, BPG, and VVC, have already reached or exceeded the encoding speed and compression ratio of traditional image coding technologies. Currently, end-to-end image coding technology has entered the standardization stage, and due to its superior performance, it is expected to be widely used in the future. In practical image coding applications, there is a need to preview the encoded data.

[0038] Generally, when previewing an image, it is not necessary to fully decode the image to obtain the original resolution. Instead, it is only necessary to observe a low-definition, small-resolution preview image. However, existing end-to-end image coding technologies do not have a method specifically for generating preview images. Therefore, it is necessary to first fully decode the encoded data to obtain the original resolution image, and then downsample the original resolution image to obtain a small-resolution preview image for reconstruction and feedback to the user. Since the decoding network used for full decoding generally has high power consumption, this will result in a large computational overhead when previewing ultra-high-definition original images with extremely high resolution and pixel count, wasting computing resources, and the preview image generation speed is slow, resulting in a poor user experience.

[0039] The image preview method provided in the disclosed embodiments can be applied to the aforementioned end-to-end image coding technology. The method trains a target coding network for the end-to-end image coding technology to obtain a target preview network capable of directly generating a low-resolution preview image. The target coding network obtains target coded data after encoding the target image. The target preview network corresponding to the target coding network decodes the target coded data, thereby directly generating a target preview image with a lower resolution that effectively preserves the semantic information of the target image. This method not only speeds up the generation of the target preview image but also meets the user's preview needs.

[0040] The image preview method provided by the embodiment of the present disclosure is described in detail below.

[0041] Figure 1 A flowchart of an image preview method according to an embodiment of the present disclosure is shown. The image preview method can be executed by an electronic device such as a terminal device or a server. The terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The image preview method can be implemented by a processor calling a computer-readable instruction stored in a memory. Alternatively, the image preview method can be executed by a server. Figure 1 As shown, the image preview method may include:

[0042] In S11, target coding data is obtained, wherein the target coding data is obtained after the target coding network performs image coding on the target image.

[0043] After the target image is encoded based on the target encoding network to obtain target encoding data, if there is a need to preview the target image, the target encoding data can be obtained so that the target encoding data can be subsequently decoded.

[0044] The target coding network here can be a coding network trained based on end-to-end image coding technology. The specific network structure and training process of the target coding network can refer to the end-to-end image coding network in the relevant technology, and this disclosure does not make specific limitations on this.

[0045] In S12, the target coding data is image decoded using the target preview network corresponding to the target coding network to obtain a target preview image corresponding to the target image, wherein the resolution of the target preview image is smaller than the resolution of the target image.

[0046] By using the target preview network corresponding to the target encoding network to decode the target encoded data, a target preview image with a lower resolution that effectively preserves the semantic information of the target image can be directly generated. The process of training the target preview image and decoding the target encoded data using the target preview network to obtain the target preview image will be described in detail later in conjunction with possible implementations of the present disclosure, and will not be further elaborated here.

[0047] In the disclosed embodiment, target coding data obtained after the target coding network performs image coding on the target image is obtained, and the target coding data is decoded using the target preview network corresponding to the target coding network, so that a target preview image with a lower resolution and better preservation of the semantic information of the target image can be directly generated, which can not only improve the generation speed of the target preview image, but also meet the preview needs of users.

[0048] In order to be able to perform image preview on the encoded data after being encoded by the target encoding network, a target preview network corresponding to the target encoding network is trained in advance.

[0049] In one possible implementation, before using the target preview network to perform image decoding on the target coded data, the image preview method further includes: using the target coding network to perform image encoding on the sample image to obtain sample coded data of the sample image; using the initial preview network to perform image decoding on the sample coded data to obtain a predicted preview image corresponding to the sample image, wherein the resolution of the predicted preview image is smaller than the resolution of the sample image; based on the predicted preview image, determining a predicted decoded image corresponding to the sample image; and using the sample image and the predicted decoded image to perform network training on the initial preview network to obtain a target preview network.

[0050] The target coding network is used to perform image coding on the sample image to obtain sample coding data of the sample image; the initial preview network is used to perform image decoding on the sample coding data to obtain a predicted preview image with a smaller resolution corresponding to the sample image; based on the predicted preview image, a predicted decoded image corresponding to the sample image is determined; the sample image and the predicted decoded image are used to perform network training on the initial preview network so that a trained target preview network can be obtained, and a preview image with a smaller resolution and better preservation of the original semantic information of the image is directly generated for the coding data of the target coding network, which can not only improve the generation speed of the preview image, but also meet the preview needs of users.

[0051] In order to complete network training, a training sample set is pre-constructed, wherein the training sample set may include sample images of various resolutions. The number of sample images included in the training sample set and the resolution of each sample image may be set according to actual conditions, and this disclosure does not impose specific limitations on this.

[0052] During the training process, at least one sample image is randomly selected from the training sample set, the sample image is input into the target coding network, and after the target coding network performs image encoding, sample encoding data of the sample image is output.

[0053] In one possible implementation, the target coding network is a coding network based on a channel grouping entropy coding algorithm, and the sample coding data is obtained by sequentially entropy coding K groups of sample channel features corresponding to the sample image, and the sample coding data includes code stream data corresponding to each group of sample channel features.

[0054] When the target coding network is a coding network based on a channel grouping entropy coding algorithm, entropy coding can be performed sequentially on the K groups of sample channel features corresponding to the sample image, fully utilizing the structural redundancy between different channel groups to improve the coding compression rate of the encoded data. The specific value of K can be determined based on actual conditions and is not specifically limited in this disclosure.

[0055] In one example, the sample image is first encoded into a sample feature tensor of H×W×C Wherein, H and W are the width and height of the spatial dimension, and C is the number of feature channels of the channel dimension. The process of encoding the sample image to obtain the sample feature tensor can refer to the image encoding process in the related art, and this disclosure does not specifically limit this.

[0056] In the target coding network based on the channel grouping entropy coding algorithm, the sample feature tensor Group in the channel dimension to obtain K groups of sample channel features The number of channels corresponding to each group of sample channel features is C1, C2, ..., C K , where C1+C2+……+CK = C. C1, C2, ..., C K The specific values of can be the same or different, and this disclosure does not make any specific limitations on this.

[0057] When entropy encoding is performed on K groups of sample channel features in sequence, except for the first group of sample channel features, the remaining any i-th group of sample channel features uses the first to i-1th groups of sample channel features that have been entropy encoded before as context information, so as to fully utilize the structural redundancy between different channel groups.

[0058] The probability estimation model in the target coding network is used to determine the entropy parameters of the first group of sample channel features, and the entropy parameters of the first group of sample channel features are used to entropy encode the first group of sample channel features to obtain code stream data of the first group of sample channel features.

[0059] After entropy encoding the first group of sample channel features, the first group of sample channel features are input into the probability estimation model to determine the entropy parameters of the second group of sample channel features, and the second group of sample channel features are entropy encoded using the entropy parameters of the second group of sample channel features to obtain code stream data of the second group of sample channel features.

[0060] After entropy encoding the second group of sample channel features, the first group of sample channel features and the second group of sample channel features are input into the probability estimation model to determine the entropy parameters of the third group of sample channel features. The third group of sample channel features are entropy encoded using the entropy parameters of the third group of sample channel features to obtain the code stream data of the third group of sample channel features.

[0061] The same process is repeated until the entropy coding of the Kth group of sample channel features is completed, which will not be described in detail here. The code stream data of the first to Kth groups of sample channel features together constitute the sample coded data of the sample image.

[0062] By using the initial preview network, the sample encoded data can be decoded to directly generate a predicted preview image corresponding to the sample image, which has a smaller resolution and can better preserve the original semantic information of the sample image.

[0063] The initial preview network here can be an initialized, untrained target preview network. That is, the initial preview network and the final trained target preview network have the same network structure, with only the network parameters potentially differing. The specific network structure of the initial preview network can be configured based on actual needs and is not specifically limited in this disclosure.

[0064] In one possible implementation, an initial preview network is used to perform image decoding on sample coded data to obtain a predicted preview image corresponding to the sample image, including: entropy decoding the sample coded data to sequentially obtain the first to Nth groups of sample channel features corresponding to the sample image, where N < K; and using the initial preview network, image decoding the first to Nth groups of sample channel features to obtain the predicted preview image.

[0065] Since the original semantic information of the sample image is concentrated in the code stream data of the first several groups of sample channel features that are entropy coded, only part of the code stream data of the first N groups of sample channel features that are entropy coded can be entropy decoded, and then only the first N groups of sample channel features obtained by decoding can be used by the initial preview network to perform image decoding. In this way, a prediction preview image with a small resolution that can better retain the original semantic information of the sample image can be directly generated, which effectively improves the speed of generating the prediction preview image.

[0066] The specific value of N can be set according to actual conditions, and this disclosure does not make any specific limitation on this.

[0067] In one possible implementation, entropy decoding is performed on sample coded data to obtain the first to Nth groups of sample channel features corresponding to the sample image, including: determining an entropy parameter of the first group of sample channel features, and using the entropy parameter of the first group of sample channel features to entropy decode the bitstream data corresponding to the first group of sample channel features to obtain the first group of sample channel features; when i>1, determining the entropy parameter of the i-th group of sample channel features based on the decoded first to i-1th groups of sample channel features, and using the entropy parameter of the i-th group of sample channel features to entropy decode the bitstream data corresponding to the i-th group of sample channel features to obtain the i-th group of sample channel features.

[0068] When entropy decoding is performed on the 1st to Nth groups of sample channel features in sequence, except for the 1st group of sample channel features, any remaining i-th group of sample channel features uses the 1st to i-1th groups of sample channel features that have previously completed entropy decoding as context information, so as to accurately decode the 1st to Nth groups of sample channel features.

[0069] The process of sequentially performing entropy decoding on the channel features of the first to Nth groups of samples is the inverse process of sequentially performing entropy encoding on the channel features of the first to Nth groups of samples.

[0070] The probability estimation model in the target coding network is used to determine the entropy parameters of the first group of sample channel features, and the entropy parameters of the first group of sample channel features are used to entropy decode the bitstream data corresponding to the first group of sample channel features to obtain the first group of sample channel features.

[0071] After decoding to obtain the first group of sample channel features, the decoded first group of sample channel features are input into the probability estimation model to determine the entropy parameters of the second group of sample channel features. The entropy parameters of the second group of sample channel features are used to entropy decode the bitstream data corresponding to the second group of sample channel features to obtain the second group of sample channel features.

[0072] After decoding to obtain the second group of sample channel features, the decoded first group of sample channel features and the second group of sample channel features are input into the probability estimation model to determine the entropy parameters of the third group of sample channel features. The entropy parameters of the third group of sample channel features are used to entropy encode the bitstream data corresponding to the third group of sample channel features to obtain the third group of sample channel features.

[0073] This process is deduced in this way until the Nth set of sample channel features is obtained through decoding, which will not be described in detail here.

[0074] In one example, after decoding to obtain the first to Nth groups of sample channel features, the first to Nth groups of sample channel features can be input into the initial preview network so that the initial preview network directly generates a predicted preview image corresponding to the sample image.

[0075] In one example, after sequentially decoding to obtain the first to Nth groups of sample channel features, a progressive decoding method may also be used to obtain N progressive prediction preview images.

[0076] For example, when the first group of sample channel features is obtained through decoding and the second to N-th groups of sample channel features are not obtained through decoding, the first progressive prediction preview image is generated; when the first to second groups of sample channel features are obtained through decoding and the third to N-th groups of sample channel features are not obtained through decoding, the second progressive prediction preview image is generated; and so on, until the N-th progressive prediction preview image is generated after the first to N-th groups of sample channel features are obtained through decoding.

[0077] In related technologies, when generating each progressive prediction preview image, it is necessary to use the probability estimation model in the target coding network to determine the entropy parameters of all undecoded sample channel features, resulting in a slow generation speed of each progressive prediction preview image, which seriously affects the user experience.

[0078] In one possible implementation, the predicted preview image includes N progressive predicted preview images; using the initial preview network, the image decoding of the first to N groups of sample channel features is performed to obtain the predicted preview image, including: when the first to i groups of sample channel features are decoded and the i+1 to N groups of sample channel features are not decoded, the entropy parameters of the i+1 to N groups of sample channel features are filled with zero values respectively to obtain the filling entropy parameters of the i+1 to N groups of sample channel features, where i≥1; the filling entropy parameters of the first to i groups of sample channel features and the i+1 to N groups of sample channel features are input into the initial preview network to obtain the i-th progressive predicted preview image.

[0079] Filling the entropy parameters of the undecoded sample channel features with zero values can effectively reduce the time for determining the entropy parameters of the undecoded sample channel features, thereby effectively increasing the generation speed of each progressive prediction preview image, reducing user waiting time, and improving user experience.

[0080] When the first group of sample channel features is obtained by decoding and the second to Nth groups of sample channel features are not obtained by decoding, the entropy parameters of the second to Nth groups of sample channel features are filled with zero values respectively to obtain the filling entropy parameters of the second to Nth groups of sample channel features; the filling entropy parameters of the first group of sample channel features and the second to Nth groups of sample channel features are input into the initial preview network to obtain the first progressive prediction preview image.

[0081] When the first to second groups of sample channel features are obtained by decoding and the third to N groups of sample channel features are not obtained by decoding, the entropy parameters of the third to N groups of sample channel features are filled with zero values respectively to obtain the filling entropy parameters of the third to N groups of sample channel features; the filling entropy parameters of the first group of sample channel features, the second group of sample channel features, and the third to N groups of sample channel features are input into the initial preview network to obtain the second progressive prediction preview image.

[0082] The process is deduced in this way until the Nth progressive prediction preview image is obtained, which will not be described in detail here.

[0083] In the embodiment of the present disclosure, in addition to the above-mentioned method of sampling only the first 1 to N groups of K groups of sample channel features corresponding to the sample image to generate a predicted preview image, a method of generating a predicted preview image using all K groups of sample channel features corresponding to the sample image can also be adopted. The embodiment of the present disclosure does not make specific limitations on this.

[0084] The resolution of the predicted preview image generated by the initial preview network can be determined based on a preset resolution ratio. For example, if the preset resolution ratio is 1:8, the resolution of the predicted preview image is 1 / 8 of the resolution of the original sample image. The specific value of the preset resolution ratio can be set based on actual conditions and is not specifically limited in this disclosure.

[0085] Since the resolution of the preview image is smaller than that of the sample image, in order to further utilize the sample image for subsequent network training, the predicted decoded image corresponding to the sample image can be determined based on the predicted preview image.

[0086] In a possible implementation, determining a predicted decoded image corresponding to a sample image based on a predicted preview image includes upsampling the predicted preview image to obtain a predicted decoded image, wherein the predicted decoded image and the sample image have the same resolution.

[0087] Since the predicted preview image has a smaller resolution than the original sample image, the predicted preview image is upsampled to obtain a predicted decoded image with the same resolution as the original sample image, so as to effectively perform subsequent comparative training.

[0088] In one example, the predicted preview image can be upsampled using a preset upsampling algorithm. The preset upsampling algorithm can be a bilinear interpolation algorithm, a nearest neighbor interpolation algorithm, or other algorithms capable of upsampling the predicted preview image, which are not specifically limited in the present embodiment.

[0089] For example, if the resolution of the predicted preview image is 1 / 8 of the resolution of the original sample image, the predicted preview image may be subjected to three consecutive bilinear interpolation processes to obtain a predicted decoded image having the same resolution as the original sample image.

[0090] In one possible implementation, the sample image and the predicted decoded image are used to perform network training on the initial preview network to obtain a target preview network, including: determining a distortion rate of the predicted decoded image relative to the sample image; and based on the distortion rate, performing network training on the initial preview network to obtain a target preview network.

[0091] After upsampling the predicted preview image output by the initial preview network to obtain a predicted decoded image, the distortion rate of the predicted decoded image relative to the sample image is determined. Based on the distortion rate, the initial preview network can be trained to optimize the network parameters of the initial preview network, thereby ultimately training the target preview network.

[0092] In one example, reducing the distortion ratio of the predicted decoded image relative to the sample image is used as the optimization objective, and this optimization objective is optimized using stochastic gradient descent. The training process is iteratively executed until the distortion ratio of the predicted decoded image relative to the sample image is less than a preset distortion ratio threshold, or the function corresponding to the distortion ratio converges, at which point training is terminated. The specific value of the preset distortion ratio threshold can be set based on actual circumstances and is not specifically limited in this disclosure.

[0093] For the above-mentioned progressive decoding method, after each progressive prediction preview image is generated, the network parameters of the initial preview network may be adjusted, and then the initial preview network with the adjusted network parameters may be used to generate the next progressive prediction preview image.

[0094] After training the target preview network corresponding to the target encoding network, the target preview network can be applied to the image preview scenario to directly generate a target preview image with a smaller resolution and better preservation of the original semantic information of the target image, based on the target encoding data obtained after the target encoding network encodes the target image.

[0095] In a possible implementation, the target coded data is obtained by sequentially entropy coding K groups of target channel features corresponding to the target image, and the target coded data includes code stream data corresponding to each group of target channel features.

[0096] In the case where the target coding network is a coding network based on a channel grouping entropy coding algorithm, the process of the target coding network performing image encoding on the target image to obtain target coding data is similar to the process of the above-mentioned target coding network performing image encoding on the sample image to obtain sample coding data, and will not be repeated here.

[0097] In one possible implementation, a target preview network corresponding to a target encoding network is used to perform image decoding on target encoded data to obtain a target preview image corresponding to the target image, including: performing entropy decoding on the target encoded data to sequentially obtain the first to Nth groups of target channel features corresponding to the target image, where N<K; and using the target preview network, performing image decoding on the first to Nth groups of target channel features to obtain the target preview image.

[0098] Since the semantic information of the target image is concentrated in the bitstream data of the first several groups of target channel features that are entropy coded, only part of the bitstream data of the first N groups of target channel features that are entropy coded can be entropy decoded, and then only the first N groups of target channel features obtained by decoding can be used by the target preview network to perform image decoding. In this way, a target preview image with a small resolution that can better retain the original semantic information of the target image can be directly generated, which effectively improves the speed of generating the target preview image.

[0099] The specific value of N is the same as the specific value of N set during the training process of training the target preview network using the partial channel feature image decoding method.

[0100] The process of entropy decoding the target coded data to obtain the first to Nth groups of target channel features corresponding to the target image is similar to the above-mentioned process of entropy decoding the sample coded data to obtain the first to Nth groups of sample channel features corresponding to the sample image, and will not be repeated here.

[0101] In one example, when the target preview network is trained using a partial channel feature image decoding method, the decoded first to Nth groups of target channel features are input into the target preview network so that the target preview network directly generates a target preview image corresponding to the target image.

[0102] In one example, when the target preview network is trained by combining partial channel feature image decoding and progressive decoding, the first to Nth groups of target channel features are decoded and input into the target preview network in sequence to obtain N progressive target preview images corresponding to the target image.

[0103] In a possible implementation, the target preview image includes N progressive target preview images; using the target preview network, the first to N groups of target channel features are image decoded to obtain the target preview image, including: when the first to i groups of target channel features are decoded and the i+1 to N groups of target channel features are not decoded, the entropy parameters of the i+1 to N groups of target channel features are zero-filled respectively to obtain the filling entropy parameters of the i+1 to N groups of target channel features, where i≥1; the filling entropy parameters of the first to i groups of target channel features and the i+1 to N groups of target channel features are input into the target preview network to obtain the i-th progressive target preview image.

[0104] Filling the entropy parameters of the undecoded target channel features with zero values can effectively reduce the time for determining the entropy parameters of the undecoded target channel features, thereby effectively increasing the generation speed of each progressive target preview image, reducing user waiting time, and improving user experience.

[0105] The process of generating N progressive target preview images using the target preview network is similar to the above-mentioned method of generating N progressive prediction preview images using the initial preview network, and will not be described in detail here.

[0106] In a possible implementation, the image preview method further includes: upsampling the target preview image to obtain a target decoded image corresponding to the target image, wherein the target decoded image has the same resolution as the target image.

[0107] The target preview image with a smaller resolution is upsampled to obtain a target decoded image with the target image resolution restored, thereby effectively meeting the user's need to view clear images with a larger resolution.

[0108] It is understood that the above-mentioned various method embodiments mentioned in this disclosure can be combined with each other to form combined embodiments without violating the principle logic. Due to space limitations, this disclosure will not go into details. It is understood by those skilled in the art that in the above-mentioned methods of specific implementation, the specific execution order of each step should be determined by its function and possible internal logic.

[0109] In addition, the present disclosure also provides an image preview device, an electronic device, a computer-readable storage medium, and a program, all of which can be used to implement any image preview method provided by the present disclosure. The corresponding technical solutions and descriptions can be found in the corresponding records in the method section and will not be repeated here.

[0110] Figure 2 FIG. 1 is a block diagram of an image preview device according to an embodiment of the present disclosure. Figure 2 As shown, the device 20 includes:

[0111] An acquisition module 21 is configured to acquire target coding data, wherein the target coding data is obtained after a target coding network performs image coding on a target image;

[0112] The image preview module 22 is used to use the target preview network corresponding to the target coding network to perform image decoding on the target coded data to obtain a target preview image corresponding to the target image, wherein the resolution of the target preview image is smaller than the resolution of the target image.

[0113] In a possible implementation, the target coding data is obtained by sequentially entropy coding K groups of target channel features corresponding to the target image;

[0114] The image preview module 22 includes:

[0115] The first entropy decoding submodule is used to perform entropy decoding on the target coded data to sequentially obtain the first to Nth groups of target channel features corresponding to the target image, where N < K;

[0116] The first image preview submodule is used to use the target preview network to perform image decoding on the first to Nth groups of target channel features to obtain a target preview image.

[0117] In a possible implementation, the target preview image includes N progressive target preview images;

[0118] The first image preview submodule is specifically used to:

[0119] When the first to i-th groups of target channel features are obtained by decoding, and the i+1-th to N-th groups of target channel features are not obtained by decoding, the entropy parameters of the i+1-th to N-th groups of target channel features are filled with zero values to obtain the filling entropy parameters of the i+1-th to N-th groups of target channel features, where i ≥ 1;

[0120] The filling entropy parameters of the target channel features from the 1st group to the i-th group and the target channel features from the i+1th group to the Nth group are input into the target preview network to obtain the i-th progressive target preview image.

[0121] In a possible implementation, the apparatus 20 further includes:

[0122] The upsampling module is used to upsample the target preview image to obtain a target decoded image corresponding to the target image, wherein the target decoded image has the same resolution as the target image.

[0123] In a possible implementation, the apparatus 20 further includes:

[0124] an encoding module, configured to, before performing image decoding on the target coded data using the target preview network, perform image encoding on the sample image using the target coding network to obtain sample coded data of the sample image;

[0125] a decoding module, configured to perform image decoding on the sample coded data using the initial preview network to obtain a predicted preview image corresponding to the sample image, wherein the resolution of the predicted preview image is smaller than the resolution of the sample image;

[0126] A determination module, configured to determine a predicted decoded image corresponding to the sample image based on the predicted preview image;

[0127] The training module is used to use sample images and predicted decoded images to perform network training on the initial preview network to obtain the target preview network.

[0128] In a possible implementation, the sample encoding data is obtained by sequentially entropy encoding K groups of sample channel features corresponding to the sample image;

[0129] Decoding module, including:

[0130] The second entropy decoding submodule is used to perform entropy decoding on the sample coded data to obtain the first to Nth groups of sample channel features corresponding to the sample image, where N < K;

[0131] The second image preview submodule is used to use the initial preview network to perform image decoding on the channel features of the first to Nth groups of samples to obtain a predicted preview image.

[0132] In a possible implementation, the sample encoding data includes code stream data corresponding to each group of sample channel features;

[0133] The second entropy decoding submodule is specifically used to:

[0134] Determining an entropy parameter of the first group of sample channel features, and performing entropy decoding on bitstream data corresponding to the first group of sample channel features using the entropy parameter of the first group of sample channel features to obtain the first group of sample channel features;

[0135] When i>1, the entropy parameters of the i-th group of sample channel features are determined based on the decoded sample channel features of the 1st group to the i-1th group, and the entropy parameters of the i-th group of sample channel features are used to entropy decode the bitstream data corresponding to the i-th group of sample channel features to obtain the i-th group of sample channel features.

[0136] In a possible implementation, the predicted preview image includes N progressive predicted preview images;

[0137] The second image preview submodule is specifically used to:

[0138] When the 1st to i-th groups of sample channel features are obtained by decoding, and the i+1th to N-th groups of sample channel features are not obtained by decoding, the entropy parameters of the i+1th to N-th groups of sample channel features are filled with zero values to obtain the filling entropy parameters of the i+1th to N-th groups of sample channel features, where i ≥ 1;

[0139] The filling entropy parameters of the sample channel features from the 1st group to the i-th group and the sample channel features from the i+1th group to the Nth group are input into the initial preview network to obtain the i-th progressive prediction preview image.

[0140] In a possible implementation, a module is determined, specifically configured to:

[0141] The predicted preview image is up-sampled to obtain a predicted decoded image, wherein the predicted decoded image and the sample image have the same resolution.

[0142] In a possible implementation, the training module is specifically configured to:

[0143] determining a distortion ratio of the predicted decoded image relative to the sample image;

[0144] Based on the distortion rate, the initial preview network is trained to obtain the target preview network.

[0145] In this embodiment, the acquisition module 21 may be a data reading device, and the image preview module 22 may be a graphics processor.

[0146] This method has a specific technical connection with the internal structure of the computer system, and can solve the technical problem of how to improve the hardware computing efficiency or execution effect (including reducing the amount of data storage, reducing the amount of data transmission, increasing the hardware processing speed, etc.), thereby obtaining the technical effect of improving the internal performance of the computer system in accordance with the laws of nature.

[0147] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0148] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium may be a volatile or non-volatile computer-readable storage medium.

[0149] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above method.

[0150] An embodiment of the present disclosure also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0151] The electronic device may be provided as a terminal, a server, or other forms of devices.

[0152] Figure 3 FIG. 1 is a block diagram of an electronic device according to an embodiment of the present disclosure. Figure 3 The electronic device 800 may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or other terminal device.

[0153] Reference Figure 3 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0154] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 802 may include one or more modules to facilitate interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

[0155] The memory 804 is configured to store various types of data to support operations on the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0156] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0157] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0158] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0159] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0160] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the electronic device 800, the relative positioning of components, such as the display and keypad of the electronic device 800. The sensor assembly 814 can also detect changes in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a complementary metal oxide semiconductor (CMOS) or charge coupled device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0161] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as wireless network (Wi-Fi), second generation mobile communication technology (2G), third generation mobile communication technology (3G), fourth generation mobile communication technology (4G), long term evolution (LTE) of universal mobile communication technology, fifth generation mobile communication technology (5G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0162] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0163] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 804 including computer program instructions. The computer program instructions can be executed by the processor 820 of the electronic device 800 to perform the above method.

[0164] The present disclosure relates to the field of augmented reality. By acquiring image information of a target object in a real-world environment, the relevant features, states, and attributes of the target object are detected or identified using various vision-related algorithms, thereby achieving an AR effect that combines virtual and real life and matches the specific application. For example, the target object may be a face, limbs, gestures, movements, etc. related to the human body, or an identifier or marker related to an object, or a sandbox, display area, or display items related to a venue or location. Vision-related algorithms may involve visual positioning, SLAM, 3D reconstruction, image registration, background segmentation, key point extraction and tracking of objects, and object pose or depth detection. Specific applications can involve not only interactive scenarios such as guided tours, navigation, explanations, reconstruction, and virtual effect overlay displays related to real scenes or objects, but also special effects processing related to people, such as makeup beautification, body beautification, special effects display, and virtual model display. Detection or identification of the relevant features, states, and attributes of the target object can be achieved using a convolutional neural network. The above-mentioned convolutional neural network is a network model obtained by model training based on a deep learning framework.

[0165] Figure 4 FIG. 1 is a block diagram showing another electronic device according to an embodiment of the present disclosure. Figure 4 , the electronic device 1900 can be provided as a server or a terminal device. Figure 4 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute the instructions to perform the above-described method.

[0166] The electronic device 1900 may further include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as a Microsoft Server operating system (Windows Server 2003). TM ), a graphical user interface operating system launched by Apple (Mac OSX TM ), a multi-user, multi-process computer operating system (Unix TM ), a free and open source Unix-like operating system (Linux TM ), an open-source Unix-like operating system (FreeBSD TM ) or similar.

[0167] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0168] The present disclosure may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0169] Computer-readable storage media can be a tangible device that can hold and store the instructions used by the instruction execution device. Computer-readable storage media can be, for example, (but not limited to) an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. Computer-readable storage media used herein is not interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagated by waveguides or other transmission media (for example, light pulses by fiber optic cables), or electrical signals transmitted by wires.

[0170] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0171] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, and conventional procedural programming languages such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., utilizing an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions. The electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0172] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0173] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0174] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0175] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the prescribed logical function. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the prescribed function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0176] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0177] The above description of the various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced with each other and will not be repeated herein for the sake of brevity.

[0178] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0179] If the technical solution of this application involves personal information, the product that applies the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing personal information. If the technical solution of this application involves sensitive personal information, the product that applies the technical solution of this application has obtained the individual's separate consent before processing sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, a clear and prominent sign is set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that they agree to the collection of their personal information; or on the personal information processing device, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload their personal information; among which, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

[0180] While various embodiments of the present disclosure have been described above, the above descriptions are illustrative, non-exhaustive, and not intended to be limiting of the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. An image preview method, characterized in that: include: Obtaining target coding data, wherein the target coding data is obtained after the target coding network performs image coding on the target image; Using a target preview network corresponding to the target encoding network, performing image decoding on the target encoded data to obtain a target preview image corresponding to the target image, wherein a resolution of the target preview image is smaller than a resolution of the target image; Before performing image decoding on the target coded data using the target preview network, the method further includes: Using the target coding network, performing image coding on the sample image to obtain sample coding data of the sample image; Using an initial preview network, performing image decoding on the sample coded data to obtain a predicted preview image corresponding to the sample image, wherein a resolution of the predicted preview image is smaller than a resolution of the sample image; Determining a predicted decoded image corresponding to the sample image based on the predicted preview image; Using the sample image and the predicted decoded image, performing network training on the initial preview network to obtain the target preview network; The target coding data is obtained by sequentially entropy coding K groups of target channel features corresponding to the target image, and the target preview image includes N progressive target preview images; The method of using a target preview network corresponding to the target encoding network to perform image decoding on the target encoded data to obtain a target preview image corresponding to the target image includes: Performing entropy decoding on the target coded data to sequentially obtain the first to Nth groups of target channel features corresponding to the target image, where N < K; When the first to i-th groups of target channel features are obtained by decoding, and the i+1-th to N-th groups of target channel features are not obtained by decoding, the entropy parameters of the i+1-th to N-th groups of target channel features are respectively filled with zero values to obtain the filling entropy parameters of the i+1-th to N-th groups of target channel features, where i≥1; The filling entropy parameters of the target channel features of the first to i groups and the target channel features of the i+1th to Nth groups are input into the target preview network to obtain the i-th progressive target preview image.

2. The method according to claim 1, further comprising: The target preview image is up-sampled to obtain a target decoded image corresponding to the target image, wherein the target decoded image has the same resolution as the target image.

3. The method according to claim 1, characterized in that The sample coded data is obtained by sequentially performing entropy coding on K groups of sample channel features corresponding to the sample image; The method of using the initial preview network to perform image decoding on the sample coded data to obtain a predicted preview image corresponding to the sample image includes: Performing entropy decoding on the sample coded data to obtain the first to Nth groups of sample channel features corresponding to the sample image, where N<K; The initial preview network is used to perform image decoding on the first to Nth groups of sample channel features to obtain the predicted preview image.

4. The method according to claim 3, characterized in that The sample coding data includes code stream data corresponding to each group of sample channel features; The entropy decoding of the sample coded data to obtain the first to Nth groups of sample channel features corresponding to the sample image includes: Determining an entropy parameter of a first group of sample channel features, and performing entropy decoding on bitstream data corresponding to the first group of sample channel features using the entropy parameter of the first group of sample channel features to obtain the first group of sample channel features; When i>1, based on the decoded sample channel features of the 1st to i-1th groups, the entropy parameters of the i-th group of sample channel features are determined, and the entropy parameters of the i-th group of sample channel features are used to entropy decode the bitstream data corresponding to the i-th group of sample channel features to obtain the i-th group of sample channel features.

5. The method according to claim 3 or 4, characterized in that The predicted preview images include N progressive predicted preview images; The method of using the initial preview network to perform image decoding on the first to Nth groups of sample channel features to obtain the predicted preview image includes: When the first to i-th groups of sample channel features are obtained by decoding, and the i+1-th to N-th groups of sample channel features are not obtained by decoding, zero-filling is performed on the entropy parameters of the i+1-th to N-th groups of sample channel features to obtain the filling entropy parameters of the i+1-th to N-th groups of sample channel features, where i ≥ 1; The filling entropy parameters of the sample channel features of the first to i-th groups and the sample channel features of the i+1-th to N-th groups are input into the initial preview network to obtain the i-th progressive prediction preview image.

6. The method according to claim 3 or 4, characterized in that The determining, based on the predicted preview image, the predicted decoded image corresponding to the sample image includes: The predicted preview image is up-sampled to obtain the predicted decoded image, wherein the predicted decoded image and the sample image have the same resolution.

7. The method according to claim 3 or 4, characterized in that The method of performing network training on the initial preview network using the sample image and the predicted decoded image to obtain the target preview network includes: determining a distortion rate of the predicted decoded image relative to the sample image; Based on the distortion rate, network training is performed on the initial preview network to obtain the target preview network.

8. An image preview device, characterized in that: include: an acquisition module, configured to acquire target coding data, wherein the target coding data is obtained after a target coding network performs image coding on a target image; an image preview module, configured to perform image decoding on the target coded data using a target preview network corresponding to the target coding network, to obtain a target preview image corresponding to the target image, wherein a resolution of the target preview image is smaller than a resolution of the target image; Wherein, the device further includes: an encoding module, configured to perform image encoding on a sample image using the target encoding network to obtain sample encoding data of the sample image; a decoding module, configured to perform image decoding on the sample coded data using an initial preview network to obtain a predicted preview image corresponding to the sample image, wherein a resolution of the predicted preview image is smaller than a resolution of the sample image; a determination module, configured to determine a predicted decoded image corresponding to the sample image based on the predicted preview image; A training module, configured to perform network training on the initial preview network using the predicted decoded image and the sample image to obtain the target preview network; The target coding data is obtained by sequentially entropy coding K groups of target channel features corresponding to the target image, and the target preview image includes N progressive target preview images; The image preview module includes: a first entropy decoding submodule and a first image preview submodule; The first entropy decoding submodule is used for: Performing entropy decoding on the target coded data to sequentially obtain the first to Nth groups of target channel features corresponding to the target image, where N < K; The first image preview submodule is used for: When the first to i-th groups of target channel features are obtained by decoding, and the i+1-th to N-th groups of target channel features are not obtained by decoding, the entropy parameters of the i+1-th to N-th groups of target channel features are respectively filled with zero values to obtain the filling entropy parameters of the i+1-th to N-th groups of target channel features, where i≥1; The filling entropy parameters of the target channel features of the first to i groups and the target channel features of the i+1th to Nth groups are input into the target preview network to obtain the i-th progressive target preview image.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images