Image generation method and device, equipment and storage medium

Abstract

The invention provides an image generation method and device, equipment and a storage medium, and relates to the technical field of image processing, and the method comprises the steps: carrying out the image quality enhancement processing of an initial image, so as to obtain a first image; performing image signal processor processing on the first image to generate a second image in a JPEG format; obtaining metadata in the second image generation process; and performing digital negative film DNG packaging on the first image based on the metadata to generate a first DNG image. Therefore, on the basis of the high-quality first image, the metadata of the second image in the JPEG format is combined, so that the effect of the generated first DNG image can be closer to that of the second image in the JPEG format, and better convenience and image quality benefits are provided for later repair processing; and powerful basic conditions are provided for photographers to obtain optimal colors and detail expressions through post-processing.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular to an image generation method, apparatus, device, and storage medium. Background Art

[0002] DNG is a RAW image format developed by Adobe. Its full name is "Digital Negative," and it aims to provide photographers with an open, standardized RAW image format. DNG saves the raw data captured by the camera sensor and converts it into an editable file format for post-processing.

[0003] In practical applications, if DNG packaging is performed directly based on RAW images and RAW images are output in DNG format, it is difficult to present rich preview effects, which will affect the photographer's flexibility in post-processing. Summary of the Invention

[0004] The present application proposes an image generation method, apparatus, device and storage medium, aiming to solve at least one of the technical problems in the related art to a certain extent.

[0005] The first embodiment of the present application provides a method for generating an image, comprising:

[0006] Performing image quality enhancement processing on the initial image to obtain a first image;

[0007] performing image signal processor processing on the first image to generate a second image in JPEG format;

[0008] Acquiring metadata during the generation process of the second image;

[0009] Based on the metadata, a digital negative DNG package is performed on the first image to generate a first DNG image.

[0010] A second embodiment of the present application provides an image generation device, including:

[0011] A first processing module, configured to perform image quality enhancement processing on the initial image to obtain a first image;

[0012] a second processing module, configured to perform image signal processor processing on the first image to generate a second image in JPEG format;

[0013] an acquisition module, configured to acquire metadata during the generation process of the second image;

[0014] The packaging module is used to perform digital negative DNG packaging on the first image based on the metadata to generate a first DNG image.

[0015] The third aspect embodiment of the present application proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the image generation method of the embodiment of the present application.

[0016] The fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the image generation method disclosed in the embodiment of the present application.

[0017] In the disclosed embodiment, the initial image is first subjected to image quality enhancement processing to obtain a first image, and then the first image is processed by an image signal processor to generate a second image in JPEG format. Then, metadata during the generation of the second image is obtained, and finally, based on the metadata, the first image is packaged as a digital negative DNG to generate a first DNG image. Thus, based on the high-quality first image and combined with the metadata of the second image in JPEG format, the generated first DNG image can have an effect closer to the second image in JPEG format, providing better convenience and image quality benefits for post-processing and providing a strong foundation for photographers to obtain the best color and detail performance in post-processing.

[0018] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and / or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0020] Figure 1 is a flowchart of a method for generating an image according to an embodiment of the present disclosure;

[0021] Figure 2 is a flowchart of another method for generating an image according to an embodiment of the present disclosure;

[0022] Figure 3 is a flowchart of another method for generating an image according to an embodiment of the present disclosure;

[0023] Figure 4 is a structural block diagram of an image generation device provided according to an embodiment of the present disclosure;

[0024] Figure 5 It is a block diagram of an electronic device used to implement the image generation method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] The following describes in detail embodiments of the present disclosure, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present disclosure and are not to be construed as limiting the present disclosure. On the contrary, the embodiments of the present disclosure include all variations, modifications, and equivalents that fall within the spirit and scope of the appended claims.

[0026] It should be noted that the execution subject of the image generation method of this embodiment can be an image generation device, which can be implemented by software and / or hardware. The device can be configured in any imaging device that can perform image processing, such as a mobile phone, laptop computer, video camera, camera, etc., which is not limited here.

[0027] Figure 1 FIG. 1 is a flow chart of a method for generating an image according to the first embodiment of the present disclosure. Figure 1 As shown, the method includes:

[0028] S101: Perform image quality enhancement processing on an initial image to obtain a first image.

[0029] The initial image is the original image that has not been processed.

[0030] The initial image may be a single frame image or multiple frames of images, which is not limited here.

[0031] The first image is an initial image with enhanced image quality.

[0032] It should be noted that there are many ways to enhance image quality, such as sharpening, contrast adjustment, bad pixel correction, black level removal, color balance adjustment, exposure adjustment, high dynamic processing, multi-frame noise reduction processing, etc., which are not limited here.

[0033] It is understandable that by enhancing the image quality of the initial image, the first image can be made clearer, more natural, brighter, more vivid, and richer in details, which is not limited here.

[0034] As a possible implementation, when enhancing the initial image quality, the initial image can be enhanced based on the image's characteristics and needs. For example, if the initial image was taken in a dark scene, such as at dusk, a multi-frame noise reduction algorithm can be used to process the initial image. This fully preserves the scene's details and color information while avoiding noise caused by the low-light environment.

[0035] S102: Process the first image using an image signal processor to generate a second image in JPEG format.

[0036] Image signal processor processing, also known as ISP processing, stands for "Image Signal Processor." It should be noted that an ISP is a chip or module specifically designed for digital image processing, integrated into imaging devices. ISP processing can perform a series of operations on acquired raw image data to improve image quality, enhance detail, adjust color, and more, though these are not specifically defined here.

[0037] The Joint Photographic Experts Group (JPEG) format is an image compression format used for continuous-tone still images. It uses a lossy compression algorithm to significantly reduce image file size while maintaining high image quality. The JPEG format is suitable for storing and transmitting photographs, images, and other visual content.

[0038] The second image is a JPEG format image obtained by performing ISP processing on the first image.

[0039] In the disclosed embodiments, an ISP chip or module (image signal processor) can be used to process the first image. This can include various processing methods, such as white balance, color correction, sharpening, denoising, and exposure control, to improve image quality and enhance details. Subsequently, the image data processed by the ISP can be compressed and encoded to generate a JPEG format image, such as using a JPEG encoder. This can reduce the size of the image file while maintaining image quality.

[0040] S103: Acquire metadata during the second image generation process.

[0041] The metadata (Meta) during the generation of the second image may include camera settings and image processing parameters for the first image. The image processing parameters include various algorithms and settings used in the image signal processor for the first image, such as color correction parameters, sharpening parameters, and noise reduction parameters. These parameters affect the quality and appearance of the second image in JPEG format.

[0042] It can be understood that obtaining metadata during the second image generation process is helpful in understanding the specific parameters and process of the second image generation process.

[0043] For example, suppose an image signal processor is used to perform noise reduction on image A and generate a JPEG image B. The metadata in this process includes at least the noise reduction algorithm type and noise reduction intensity. For example, the noise reduction algorithm type is the wavelet noise reduction algorithm, and the noise reduction intensity is 30%, indicating that 30% of the noise is reduced.

[0044] It should be noted that the above example is only an illustrative description. There may be a lot of metadata in the second image generation process, which will not be described in detail here.

[0045] S104: Based on the metadata, perform digital negative DNG packaging on the first image to generate a first DNG image.

[0046] The first DNG image may be an image obtained by performing DNG encapsulation on the first image in combination with metadata in a process of generating the second image.

[0047] Among them, DNG is an open lossless raw image format that can retain more image details and information, providing greater flexibility and space for post-processing.

[0048] DNG packaging combines image data with related metadata to create a DNG format image file. This packaging method integrates the original image data and image parameter information into a single file, allowing for greater image detail and flexibility in post-processing.

[0049] Because metadata records relevant information about the second image, including shooting conditions, camera settings, image processing parameters, etc., it is very important for image management and subsequent use. By using metadata in DNG packaging, this information can be used as reference information for the first DNG image, facilitating subsequent management and use.

[0050] It can be understood that applying the JPEG metadata and the data of the first image to the DNG tag and finally forming a first DNG image in DNG format can make the basic effect of the first DNG image close to the JPEG image formed at the same time, which is convenient for the photographer to perform later repair processing.

[0051] In the disclosed embodiment, the initial image is first subjected to image quality enhancement processing to obtain a first image, and then the first image is processed by an image signal processor to generate a second image in JPEG format. Then, metadata during the generation of the second image is obtained, and finally, based on the metadata, the first image is packaged as a digital negative DNG to generate a first DNG image. Thus, based on the high-quality first image and combined with the metadata of the second image in JPEG format, the generated first DNG image can have an effect closer to the second image in JPEG format, providing better convenience and image quality benefits for post-processing and providing a strong foundation for photographers to obtain the best color and detail performance in post-processing.

[0052] Figure 2 FIG. 1 is a flow chart of a method for generating an image according to the second embodiment of the present disclosure. Figure 2 As shown, the method includes:

[0053] S201: Determine the shooting scene type of the initial image.

[0054] The shooting scene type may be the scene type of the environment in which the imaging device is located when the initial image is shot, such as a high dynamic scene, a dark scene, a night dynamic scene, etc., which is not limited here.

[0055] High dynamic range (HDR) scenes are also known as high dynamic range (HDR) scenes. It should be noted that in HDR scenes, the image brightness range is very wide, including very bright and very dark areas. This can be caused by factors such as lighting conditions, reflections, and shadows, such as sunsets outdoors or backlighting indoors.

[0056] The following are some specific examples of high-dynamic scenes, such as the sky and horizon at sunset or sunrise, indoor and outdoor landscapes under indoor lighting, reflection scenes from reflectors or mirrors, high-contrast light and shadow of urban buildings, the interweaving of light and shadow in mountains or canyons, sunlight reflections in rivers or lakes, shadows formed by sunlight filtering through leaves in a forest, and the light and shadows after a rainbow appears. We will not go into details here.

[0057] In dark scenes, the light is dim and the captured images may have problems such as noise, blur or low contrast.

[0058] Some specific examples of dark scenes are given below, such as the starry sky at night, low-light indoor environments, city streets at night, scenery at dusk, candlelight in a room, moonlit scenery, stage lights at a party or performance, and cloudy or overcast outdoor environments. They are not listed in detail here.

[0059] Among them, night dynamic scenes refer to scenes with dynamic elements captured at night or in dimly lit environments, such as night markets, traffic flows, fireworks, etc.

[0060] The following are some specific examples of dynamic night scenes, such as the traffic and tracks in a city at night, the hustle and bustle of a night market, the scene of fireworks, the lights and crowds in a bar or nightclub, the ships coming and going in a port or dock, neon signs at night, nighttime activities in a city park, and busy traffic intersections at night. We will not go into details here.

[0061] As a possible implementation method, the scene brightness of the shooting scene of the initial image can be first detected, and then the adaptive dynamic range control (ADRC) gain of the shooting scene can be obtained. Then, the shooting scene type of the initial image can be determined based on the scene brightness and the ADRC gain.

[0062] ADRC gain typically depends on the camera's automatic exposure system and related settings. ADRC gain adjustment aims to optimize the image's dynamic range, enabling better detail preservation and a more balanced exposure in high-contrast scenes. In some imaging devices, the automatic exposure system can dynamically adjust ADRC gain based on the brightness distribution and contrast characteristics of the scene.

[0063] Optionally, the brightness of the shooting scene of the initial image may be measured based on a brightness sensor.

[0064] Specifically, scene brightness thresholds may be pre-set, such as a first brightness threshold, a second brightness threshold, a third brightness threshold, and a fourth brightness threshold, wherein the values ​​of the first brightness threshold, the second brightness threshold, the third brightness threshold, and the fourth brightness threshold are increasing.

[0065] If the scene brightness is lower than or equal to the first brightness threshold, it means that the scene brightness is extremely low; if the scene brightness is greater than the first brightness threshold and lower than or equal to the second brightness threshold, it means that the scene brightness is low; if the scene brightness is greater than or equal to the fourth brightness threshold, it means that the scene brightness is extremely high; if the scene brightness is less than the fourth brightness threshold and greater than or equal to the third brightness threshold, it means that the scene brightness is high; if the scene brightness is between the second brightness threshold and the third brightness threshold, it means that the scene brightness is moderate, which is not limited here. Similarly, the ADRC gain can also be judged as low, moderate, high, extremely low or extremely high based on the numerical range mapped by the ADRC gain, or the change of the ADRC gain (such as whether there is adaptive adjustment) can also be judged, which is not limited here.

[0066] It's important to note that in high-dynamic-range scenes, there are often both bright and dark areas, with high contrast between these areas. In these situations, the ADRC gain will adaptively adjust based on the brightness of each area to ensure that details in all areas of the image are well preserved. Therefore, by monitoring the ADRC gain changes and whether there is significant adaptive adjustment, you can determine whether the current shooting scene is a high-dynamic-range scene.

[0067] In dark scenes, the brightness of the entire scene is relatively low. At this time, the ADRC gain may be relatively high to increase the brightness of the image and capture more details. Therefore, by detecting the value of the ADRC gain, if the value is high, it can be determined that the current shooting scene is a dark scene.

[0068] In night scenes, the overall brightness is relatively low, but there may be bright point light sources (such as buildings and streetlights), resulting in a high dynamic range. In these situations, the camera automatically adjusts exposure compensation and ADRC gain to ensure that both bright and dark areas in the image are well preserved. Therefore, by detecting the ADRC gain value and combining it with brightness information, it is possible to determine whether the current shooting scene is a night scene with dynamic range.

[0069] It should be noted that scene type recognition may be affected by many factors, such as lighting, color, contrast, etc. Therefore, the above method is for reference only, and the specific effect may vary depending on factors such as equipment and environment.

[0070] In summary, different shooting scene types can be automatically identified by analyzing the brightness information and brightness changes of the image and combining the adjustment of the ADRC gain, making the identification of the shooting scene type more reliable and accurate.

[0071] S202: Determine a corresponding image quality enhancement algorithm according to the shooting scene type.

[0072] The image quality enhancement algorithm is any image processing algorithm used to improve image quality, and is not limited thereto.

[0073] Optionally, an image quality enhancement algorithm corresponding to the current shooting scene type may be determined based on a preset mapping relationship.

[0074] Optionally, when the shooting scene type is a high-dynamic scene, it may be determined that the image quality enhancement method associated with the shooting scene type is a high-dynamic processing algorithm.

[0075] Alternatively, when the shooting scene type is a dark scene, it is determined that the image quality enhancement algorithm associated with the shooting scene type is a multi-frame noise reduction processing algorithm.

[0076] Alternatively, when the shooting scene type is a night scene dynamic scene, it is determined that the image quality enhancement algorithm associated with the shooting scene type includes a multi-frame noise reduction processing algorithm and a high dynamic processing algorithm.

[0077] High dynamic range (HDR) processing is a technique used to process high dynamic range images, aiming to address the problem of detail loss or underexposure caused by large brightness differences in traditional image processing. High dynamic range processing algorithms include exposure fusion, tone mapping, multiple exposure fusion, and local contrast enhancement, which are not discussed here. The specific HDR processing algorithm chosen can be determined based on specific needs.

[0078] Among them, the multi-frame noise reduction processing algorithm is a technology that uses multiple image frames for noise reduction, reducing noise and improving image quality by combining information from multiple input images, such as the averaging method, median filtering method, weighted averaging method, and noise reduction algorithm based on machine learning, which are not limited here.

[0079] It should be noted that for other shooting scene types, corresponding image quality enhancement algorithms can also be selected for processing, so as to specifically solve the defects and pain points encountered in the shooting scene types, which will not be elaborated here.

[0080] S203: Performing image quality enhancement processing on the initial image based on an image quality enhancement algorithm to obtain a first image.

[0081] Specifically, when the shooting scene type is a high-dynamic scene, the device can enhance the image quality of the initial image based on the high-dynamic processing algorithm. When the shooting scene type is a dark scene, the device can enhance the image quality of the initial image based on the multi-frame noise reduction processing algorithm. When the shooting scene type is a night scene dynamic scene, the device can enhance the image quality of the initial image based on the multi-frame noise reduction processing algorithm and the high-dynamic processing algorithm.

[0082] As a possible implementation manner, after generating the first image, the device may directly perform DNG packaging on the first image to generate a second DNG image.

[0083] The second DNG image is an image file obtained by directly performing DNG packaging on the first image.

[0084] Specifically, relevant metadata, including shooting time, image processing parameters, camera settings and other information, may be first extracted from the first image, and then the first image and the metadata related to the first image may be combined and packaged together to form a second DNG image.

[0085] S204: Perform image signal processing on the first image to generate a second image in JPEG format.

[0086] S205: Acquire metadata during the second image generation process.

[0087] S206: Based on the metadata, perform digital negative DNG packaging on the first image to generate a first DNG image.

[0088] It should be noted that the specific implementation of steps S204-S206 can refer to the above embodiment and will not be described in detail here.

[0089] Figure 3 This is a flowchart of a method for generating an image. Figure 3 As shown, scene detection is first performed to determine whether the scene is a high-dynamic scene, a dark scene, a night scene, or other. If it is determined to be a high-dynamic scene, a high-dynamic processing method is applied; if it is determined to be a dark scene, a multi-frame noise reduction method is applied; if it is determined to be a night scene, multi-frame noise reduction and high-dynamic processing are applied. After obtaining the first image, it can be divided into two paths: one is processed by ISP to obtain a second image in JPEG format, and the other is processed by DNG packaging and combined with the metadata generated when the second image was generated to generate the first DNG image.

[0090] In the disclosed embodiment, the shooting scene type of the initial image is first determined, and then a corresponding image quality enhancement algorithm is determined based on the shooting scene type. Then, based on the image quality enhancement algorithm, the initial image is subjected to image quality enhancement processing to obtain a first image. The first image is then processed by an image signal processor to generate a second image in JPEG format. Metadata during the generation of the second image is then obtained. Finally, based on the metadata, the first image is packaged as a digital negative DNG to generate a first DNG image. In this way, the shooting scene can be judged and distinguished, and corresponding processing methods can be adapted to different scenes to enhance the image quality of the initial image, thereby achieving a high-quality RAW image, i.e., the first image. Based on the identification result of the shooting scene type, the pain points of the shooting scene type can be targetedly addressed, thereby achieving the effect of improving the image quality of the initial image. Combined with the metadata released by the ISP processing of the first image, the effectiveness and pertinence of the DNG file tag are enriched, so that the DNG format image has a higher quality basic effect, which is more conducive to the photographer's expression of their creativity and realization of their own visual style in post-processing.

[0091] Figure 4FIG is a schematic diagram of an image generation device according to another embodiment of the present disclosure. Figure 4 As shown, the image generating device 400 includes:

[0092] A first processing module 410 is configured to perform image quality enhancement processing on the initial image to obtain a first image;

[0093] A second processing module 420 is configured to perform image signal processor processing on the first image to generate a second image in JPEG format;

[0094] An acquisition module 430 is configured to acquire metadata during the generation of the second image;

[0095] The packaging module 440 is configured to perform digital negative DNG packaging on the first image based on the metadata to generate a first DNG image.

[0096] Optionally, the first processing module includes:

[0097] a first determining unit, configured to determine a shooting scene type of the initial image;

[0098] A second determining unit, configured to determine a corresponding image quality enhancement algorithm according to the shooting scene type;

[0099] An acquiring unit is configured to perform image quality enhancement processing on the initial image based on the image quality enhancement algorithm to acquire the first image.

[0100] Optionally, the second determining unit is specifically configured to:

[0101] In a case where the shooting scene type is a high dynamic scene, determining that the image quality enhancement method associated with the shooting scene type is a high dynamic processing algorithm;

[0102] Alternatively, when the shooting scene type is a dark scene, determining that the image quality enhancement algorithm associated with the shooting scene type is a multi-frame noise reduction processing algorithm;

[0103] Alternatively, when the shooting scene type is a night scene dynamic scene, it is determined that the image quality enhancement algorithm associated with the shooting scene type includes the multi-frame noise reduction processing algorithm and the high dynamic processing algorithm.

[0104] Optionally, the first determining unit is specifically configured to:

[0105] detecting the scene brightness of the shooting scene of the initial image;

[0106] Obtaining an adaptive dynamic range control (ADRC) gain for the shooting scene;

[0107] The shooting scene type of the initial image is determined according to the scene brightness and the ADRC gain.

[0108] Optionally, get unit, also used to:

[0109] Perform DNG packaging on the first image to generate a second DNG image.

[0110] In the disclosed embodiment, the initial image is first subjected to image quality enhancement processing to obtain a first image, and then the first image is processed by an image signal processor to generate a second image in JPEG format. Then, metadata during the generation of the second image is obtained, and finally, based on the metadata, the first image is packaged as a digital negative DNG to generate a first DNG image. Thus, based on the high-quality first image and combined with the metadata of the second image in JPEG format, the generated first DNG image can have an effect closer to the second image in JPEG format, providing better convenience and image quality benefits for post-processing and providing a strong foundation for photographers to obtain the best color and detail performance in post-processing.

[0111] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0112] Figure 5 A block diagram of an exemplary computer device suitable for implementing embodiments of the present application is shown. Figure 5 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0113] like Figure 5 As shown, computer device 12 is implemented as a general-purpose computing device. Components of computer device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 that connects various system components (including system memory 28 and processing unit 16).

[0114] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of such architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnection (PCI) bus.

[0115] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0116] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be configured to read and write non-removable, non-volatile magnetic media ( Figure 5 Not shown, often called a "hard drive").

[0117] although Figure 5 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a Compact Disc Read Only Memory (hereinafter referred to as: CD-ROM), a Digital Video Disc Read Only Memory (hereinafter referred to as: DVD-ROM), or other optical media) may be provided. In these cases, each drive can be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the various embodiments of the present application.

[0118] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 42 generally implement the functions and / or methods of the embodiments described herein.

[0119] The computer device 12 can also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). This communication can occur via an input / output (I / O) interface 22. Furthermore, the computer device 12 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via a bus 18. It should be understood that, although not shown, other hardware and / or software modules can be used in conjunction with the computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0120] The processing unit 16 executes programs stored in the system memory 28 to perform various functional applications and data processing, such as implementing the image generation method mentioned in the above embodiment.

[0121] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0122] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

[0123] It should be noted that, in the description of this application, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0124] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0125] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0126] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0127] In addition, the functional units in the various embodiments of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disk, etc.

[0128] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0129] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for generating an image, characterized in that: include: Performing image quality enhancement processing on the initial image to obtain a first image; performing image signal processor processing on the first image to generate a second image in JPEG format; Acquiring metadata during the generation process of the second image; Based on the metadata, a digital negative DNG package is performed on the first image to generate a first DNG image.

2. The method according to claim 1, characterized in that The performing image quality enhancement processing on the initial image to obtain the first image includes: Determining a shooting scene type of the initial image; Determining a corresponding image quality enhancement algorithm according to the shooting scene type; Based on the image quality enhancement algorithm, image quality enhancement processing is performed on the initial image to obtain the first image.

3. The method according to claim 2, characterized in that The determining of a corresponding image quality enhancement algorithm according to the shooting scene type includes: In a case where the shooting scene type is a high dynamic scene, determining that the image quality enhancement method associated with the shooting scene type is a high dynamic processing algorithm; Alternatively, when the shooting scene type is a dark scene, determining that the image quality enhancement algorithm associated with the shooting scene type is a multi-frame noise reduction processing algorithm; Alternatively, when the shooting scene type is a night scene dynamic scene, it is determined that the image quality enhancement algorithm associated with the shooting scene type includes the multi-frame noise reduction processing algorithm and the high dynamic processing algorithm.

4. The method according to claim 2, characterized in that The determining the shooting scene type of the initial image includes: detecting the scene brightness of the shooting scene of the initial image; Obtaining an adaptive dynamic range control (ADRC) gain for the shooting scene; The shooting scene type of the initial image is determined according to the scene brightness and the ADRC gain.

5. The method according to claim 2, characterized in that After performing image quality enhancement processing on the initial image based on the image quality enhancement algorithm to obtain the first image, the method further includes: Perform DNG packaging on the first image to generate a second DNG image.

6. An image generating device, characterized in that: include: A first processing module, configured to perform image quality enhancement processing on the initial image to obtain a first image; a second processing module, configured to perform image signal processor processing on the first image to generate a second image in JPEG format; an acquisition module, configured to acquire metadata during the generation process of the second image; The packaging module is used to perform digital negative DNG packaging on the first image based on the metadata to generate a first DNG image.

7. The device according to claim 6, characterized in that The first processing module includes: a first determining unit, configured to determine a shooting scene type of the initial image; A second determining unit, configured to determine a corresponding image quality enhancement algorithm according to the shooting scene type; An acquiring unit is configured to perform image quality enhancement processing on the initial image based on the image quality enhancement algorithm to acquire the first image.

8. The device according to claim 7, characterized in that The second determining unit is specifically configured to: In a case where the shooting scene type is a high dynamic scene, determining that the image quality enhancement method associated with the shooting scene type is a high dynamic processing algorithm; Alternatively, when the shooting scene type is a dark scene, determining that the image quality enhancement algorithm associated with the shooting scene type is a multi-frame noise reduction processing algorithm; Alternatively, when the shooting scene type is a night scene dynamic scene, it is determined that the image quality enhancement algorithm associated with the shooting scene type includes the multi-frame noise reduction processing algorithm and the high dynamic processing algorithm.

9. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.

Images