22 results about "Inverse tone mapping" patented technology

A method for inverse tone mapping includes obtaining a histogram of a low dynamic range image, called LDR image and obtaining an ITMO function, allowing obtaining a pixel value of a High Dynamic Range image, called HDR image, from a pixel value of the LDR image and a gain function depending on said pixel value of the LDR image. A search process is applied using the obtained histogram to identify areas of the LDR image producing bright areas in the HDR image when the ITMO function is applied on said LDR image. Information representative of the bright areas is used to determine when modifying the gain function to ensure the HDR image respects at least one predefined light energy constraint.

The present application relates to a kind of high dynamic range illumination estimation method, device and storage medium, utilize the spatiotemporal generation prior of video generation model, by constructing "in-video drawing" task, from ordinary low dynamic range video sequence, restore time sequence consistent and physically realistic high dynamic range environment map.The input video is applied mask and combined with specific text prompt, guide model to generate virtual light probe containing surrounding environment reflection information in picture center;Variational autoencoder of high dynamic range perception is constructed, by introducing learnable tone mapping and inverse tone mapping adapter, so that video diffusion model can directly understand and output high dynamic range illumination characteristics in logarithmic domain latent space.The present application can output high-quality dynamic high dynamic range environment sequence, when processing dynamic scene, fast camera motion and complex occlusion, it has stronger robustness, applicable to augmented reality, virtual object implantation and scene relighting etc.Application.

The invention relates to a high-dynamic-range illumination estimation method and device and a storage medium, and aims to recover a physically real high-dynamic-range environment map with consistent time sequence from a common low-dynamic-range video sequence by utilizing space-time generation prior of a video generation model and constructing a video interior drawing task. Applying a mask to an input video, and guiding the model to generate a virtual optical probe containing surrounding environment reflection information in the center of a picture in combination with a specific text prompt; a high dynamic range perception variational auto-encoder is constructed, and a learnable tone mapping and inverse tone mapping adapter is introduced to enable a video diffusion model to directly understand and output high dynamic range illumination features in a logarithm domain submerged space. According to the method, a high-quality dynamic high-dynamic range environment sequence can be output, higher robustness is achieved when dynamic scenes, rapid camera motion and complex shielding are processed, and the method is suitable for application such as augmented reality, virtual object implantation and scene re-illumination.

The invention relates to a scene brightness determination method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a first SDR image and a second SDR image shot for a target scene; performing inverse tone mapping processing on the first SDR image to obtain a first HDR image, and performing inverse tone mapping processing on the second SDR image to obtain a second HDR image; and determining the actual brightness of the target scene based on the first shooting parameter of the first SDR image, the second shooting parameter of the second SDR image, the brightness of the first HDR image and the brightness of the second HDR image. By adopting the method, the actual brightness of the shooting scene can be accurately determined.

This application provides a video processing method, an electronic device, and a storage medium. In this method, for a video image frame, the electronic device determines an inverse tone mapping curve corresponding to the video image frame to obtain a grayscale gain value corresponding to the video image frame, and simultaneously determines a pixel compression coefficient corresponding to the video image frame. Then, the electronic device processes a preset 3D LUT based on the grayscale gain value and the pixel compression coefficient to obtain a target 3D LUT corresponding to the video image frame, and processes the video image frame according to the target 3D LUT. The electronic device then increases the screen backlight brightness and displays the video image frame processed by the target 3D LUT, thereby achieving a display effect that expands the dynamic range of the video image frame.

The embodiment of the invention provides a video processing method and electronic equipment. In the method, the electronic equipment can perform inverse tone mapping processing on the picture frame in the video, and the gray-scale value distribution of the pixels in the picture frame in each channel is mapped into wider gray-scale value distribution, so that the pixels can be expressed by wider gray-scale values. In this way, the picture frame in the SDR video can represent more colors, and a larger dynamic range is presented. When the video subjected to inverse tone mapping processing is played, in order to enable a user to feel a more real and vivid picture effect, the electronic equipment can improve the brightness of a screen area (a screen area 1) used for playing the video according to a certain ratio (marked as ratio 0), so that the brightness of the screen area 1 is greater than that of the screen area 1 in time 1, and the user experience is improved. Therefore, changes of picture frames in the video can be adapted. The time 1 is the time when the video playing operation is detected.

One embodiment provides a computer-implemented method that includes employing a de-banding process based on image statistics in a dynamic range conversion system, including high dynamic range (HDR) to standard dynamic range (SDR) tone mapping (TM) process or SDR-to-HDR inverse tone mapping (ITM) process. A computing device performs the de-banding process in post-processing during a determination of one or more initial ITM explicit polynomial curve coefficients. One or more parameters of a weighing function of the one or more initial ITM explicit curve coefficients are utilized as one or more controlling knots for balancing a de-banding effect and preserving local detail.

This invention provides a method and apparatus for preserving the original colors of textures. The method includes: acquiring texture data of a target to be rendered; performing an inverse tone mapping transformation on the texture data whose original colors need to be preserved to obtain inverse tone-mapped texture data; applying the inverse tone-mapped texture data to the target to be rendered; and tone mapping the inverse tone-mapped texture data to a low dynamic range in a high dynamic range pipeline. This invention performs an inverse tone mapping transformation on the texture data whose original colors need to be preserved without modifying the high dynamic range rendering pipeline itself. This eliminates the need for artists to modify textures during the high dynamic range rendering process, significantly saving manpower and time. Moreover, it only affects the transformation of texture data throughout the rendering process, without altering the overall rendering flow, thus ensuring that the target to be rendered can effectively enable glow effects and guaranteeing the realism of the rendered target.

The invention provides a method for inverse tone mapping, the method being performed by: obtaining (42) a gain function of a first inverse tone mapping function, referred to as an initial gain function; if (43) an analysis of a current image shows that at least one pixel of the current image having a luminance value at least equal to a predetermined percentage of luminance values (TH1) of the pixels of the current image has an expanded luminance value resulting from the application of the first ITM function to the current image which is higher than a target value, applying (45) to the current image a second ITM function, the second ITM function corresponding to the first inverse tone mapping function in which the gain function has been replaced by a modified gain function derived from the initial gain function in which the gain provided by the initial gain function is attenuated by an attenuation function, the attenuation function being weighted by a weighting factor controlling the intensity of the attenuation, the weighting factor depending on a statistical distribution of luminance values between the maximum luminance value in a histogram of the current image and the luminance value depending on the predetermined percentage.

The invention discloses a video inverse tone mapping highlight reconstruction method and system and a storage medium. The method comprises the following steps: inputting an SDR video frame into an HDR preliminary reconstruction network to obtain an initial HDR video frame; obtaining HDR domain features by using a domain feature enhancement network; obtaining potential features corresponding to the SDR video frames by using a diffusion model; and performing feature domain alignment and mask feature fusion on the potential feature and the HDR domain feature by using a domain alignment network to obtain a domain alignment feature and a mask fusion feature, and generating an HDR video frame according to the domain alignment feature and the mask fusion feature. According to the method and the system disclosed by the invention, the HDR video preliminary reconstruction is firstly carried out on the input SDR video, then the detail enhancement is carried out on the HDR video subjected to the preliminary reconstruction, and the diffusion model is introduced to carry out targeted fine adjustment on the HDR domain features, so that the detail recovery effect of inverse tone mapping in a high-brightness and overexposure region is improved, and the HDR video is obtained.

A method comprises: obtaining (140) reconstructed SDR data and metadata representing a first inverse tone mapping function, the first inverse tone mapping function allowing the reconstructed SDR data to be transformed into HDR data having a dynamic range, the dynamic range having a first peak luminance; deriving (141) a second tone mapping function using the metadata, the second tone mapping function allowing the SDR data to be transformed into HDR data having a dynamic range, the dynamic range having a second peak luminance lower than the first peak luminance; reconstructing (143) the HDR data using the second tone mapping function, the HDR data intended to be displayed on the display device; wherein the second peak brightness is lower than third peak brightness supported by the display equipment.

A low complexity deep neural network for inverse tone mapped image generation using mixed data is provided. A method includes: obtaining (1330) standard dynamic range (SDR) picture data; and applying (1331) a neural network implementing an inverse tone mapping process to the SDR picture data to obtain high dynamic range (HDR) picture data, where the neural network comprises a cascade of an array of samples representing the SDR picture data and an array of samples representing at least one statistical representation of the SDR picture data.

This invention discloses a video processing method and apparatus. According to one embodiment, the video processing method includes the following steps: receiving a video comprising multiple temporal portions; receiving first model parameters corresponding to a first neural network used for overall processing of the video; receiving residuals between the first model parameters and multiple second model parameters corresponding to multiple second neural networks used to process the multiple temporal portions respectively; and performing at least one of super-resolution, inverse tone mapping, tone mapping, frame interpolation, motion deblurring, denoising, and compression artifact removal on the video based on the residuals.

To enable better quality decoding of HDR images which are communicated as corresponding LDR images plus luma mapping functions, applicant teaches an encoder for encoding a high dynamic range image (Im_HDR_PSEU), which high dynamic range image is represented firstly by a matrix of pixel colors (Y_SDR, Cb_SDR, Cr_SDR) of an image of lower dynamic range (Im_SDR) than the high dynamic range image, which image of lower dynamic range gets compressed for communication as a compressed lower dynamic range image (Im_C), and also represented secondly by metadata (SEI) of the image which comprises a luma mapping function for calculating high dynamic range pixel lumas (Y_HDR) of the high dynamic range image by applying the function to pixel lumas of the image of lower dynamic range, wherein the encoder comprises an input (997) for receiving the luma mapping function (LMF) from an inverse tone mapping system (200), which is arranged to derive said luma mapping function based on analyzed properties of a master low dynamic range image (Im_LDR_mastr) for constructing the corresponding high dynamic range image (Im_HDR_PSEU), characterized in that the encoder comprises a mapping splitting unit (901) arranged to transform the luma mapping function into a stretched luma mapping function (LMF_HS) which has a shape which maps a maximum normalized input to a maximum normalized output, and arranged to determine a scaling value (SCAL), the encoder having a formatter (104) arranged to output this stretched luma mapping function (LMF_HS) and this scaling value (SCAL) as metadata of the image of lower dynamic range (Im_SDR) which is also output.

This disclosure provides a method for inverse tone mapping, the method comprising: obtaining (41) a histogram of a low dynamic range image, referred to as an LDR image; obtaining (42) an ITMO function, thereby allowing pixel values ​​of a high dynamic range image, referred to as an HDR image, to be obtained from pixel values ​​of the LDR image and a gain function dependent on the pixel values ​​of the LDR image; applying a search process using the obtained histogram to identify regions of the LDR image that produce bright areas in the HDR image when the ITMO function is applied to the LDR image, thereby using information representing the bright areas to determine when to modify the gain function to ensure that the HDR image complies with at least one predefined light energy constraint.

To enable better quality decoding of HDR images which are communicated as corresponding LDR images plus luma mapping functions, applicant teaches an encoder for encoding a high dynamic range image (Im_HDR_PSEU), which high dynamic range image is represented firstly by a matrix of pixel colors (Y_SDR, Cb_SDR, Cr_SDR) of an image of lower dynamic range (Im_SDR) than the high dynamic range image, which image of lower dynamic range gets compressed for communication as a compressed lower dynamic range image (Im_C), and also represented secondly by metadata (SEI) of the image which comprises a luma mapping function for calculating high dynamic range pixel lumas (Y_HDR) of the high dynamic range image by applying the function to pixel lumas of the image of lower dynamic range, wherein the encoder comprises an input (997) for receiving the luma mapping function (LMF) from an inverse tone mapping system (200), which is arranged to derive said luma mapping function based on analyzed properties of a master low dynamic range image (Im_LDR_mastr) for constructing the corresponding high dynamic range image (Im_HDR_PSEU), characterized in that the encoder comprises a mapping splitting unit (901) arranged to transform the luma mapping function into a stretched luma mapping function (LMF_HS) which has a shape which maps a maximum normalized input to a maximum normalized output, and arranged to determine a scaling value (SCAL), the encoder having a formatter (104) arranged to output this stretched luma mapping function (LMF_HS) and this scaling value (SCAL) as metadata of the image of lower dynamic range (Im_SDR) which is also output.

The invention discloses an inverse tone mapping method and system based on source representation learning, a terminal and a storage medium. The method comprises the following steps: acquiring an SDR video frame; based on a preset source representation dictionary, performing inverse tone mapping on the SDR video frame by using a video inverse tone mapping model based on source representation learning, and predicting to obtain an HDR video frame; and outputting the HDR video frame. According to the method, the source representation dictionary which is more accurate in learning and high in interpretability is constructed, the source representation dictionary is used for guiding the video inverse tone mapping model based on source representation learning to convert SDR videos of different sources, HDR videos with higher quality are generated, and the reconstruction quality of the HDR videos under the multi-dimensional condition is improved.

This application provides an image processing method, apparatus, and device. The method includes: acquiring a first image and display parameters of a display device, wherein the first image is a standard dynamic range (SDR) image and the display device is a high dynamic range (HDR) device; adjusting the brightness and saturation of the first image according to the display parameters to obtain a second image, wherein the display parameters include at least: display peak brightness (DPL) and / or backlight percentage. In the above process, by using an inverse tone mapping method based on brightness and saturation adjustment, the SDR image is converted into an HDR image that matches the HDR device, thus optimizing the display effect of the SDR image on the HDR device.

A method comprising obtaining a standard dynamic range (SDR) picture data; and, applying a neural network implementing an inverse tone mapping process to the SDR picture data to obtain high dynamic range (HDR) picture data, wherein the neural network comprises a concatenation of an array of samples representing the SDR picture data to an array of samples representative of at least one statistical representation of the SDR picture data.

This invention discloses a method, apparatus, and device for generating halo effects on a mobile device, comprising: acquiring an original image and extracting highlight regions from the original image to obtain highlight image attachments; performing inverse tone mapping on the highlight image attachments to obtain high dynamic range (HDR) brightened image attachments; performing multiple downsampling on the brightened image attachments to generate multiple downsampled image attachments with different resolutions; performing blurring processing on the brightened image attachments and each downsampled image attachment to obtain corresponding multiple blurred image attachments; upsampling and superimposing each blurred image attachment to generate a HDR halo composite attachment; performing tone mapping processing on the halo composite attachment to obtain a standard dynamic range (SDR) standard halo attachment; and superimposing the standard halo attachment with the original image based on the highlight image attachment to obtain the halo result image. This method can balance the visual realism of the halo effect with real-time processing performance under limited computing power.

A method comprising: obtaining (40) picture data in a first dynamic range; determining (41) a first function allowing the picture data to be mapped from the first dynamic range to a second dynamic range; signaling (42) metadata in the video data, the metadata allowing a second function to be obtained, the second function corresponding to an approximate version of the first function; determining (43) a third function from the first function and the second function such that applying the second function to intermediate data is equivalent to applying the first function to the picture data in the first dynamic range, the intermediate data is generated by applying the third function to the picture data in the first dynamic range; and signaling (44) data representing the intermediate data in the video data.

The invention discloses a video inverse tone mapping method and system, terminal equipment and a medium, and relates to the technical field of video image processing. The method comprises the following steps: converting a video frame SDR image to be reconstructed from an RGB color space to an ICtCp color space, and decoupling the video frame SDR image into a brightness channel and a chrominance channel; performing brightness hierarchical mapping processing on the brightness channel to obtain an HDR image brightness channel after dynamic range expansion; performing chromaticity mapping processing on the chromaticity channel to obtain an HDR image chromaticity channel after color gamut expansion; and combining the two channels and converting the two channels to an RGB color space to obtain a reconstructed HDR image. Brightness and chromaticity decoupling is realized based on the ICtCp space, light weight and processing precision are considered, end side deployment is adapted, the dynamic range and color gamut of the video are effectively expanded, highlight and dark part details are recovered, and the visual effect is improved.