238 results about "Tone mapping" patented technology

The invention discloses a high-precision image processing method and system based on illumination adaptive compensation, and relates to the technical field of computer vision and image processing, and the method comprises the steps: inputting an original image, and dividing the image into a high-frequency edge layer, an intermediate-frequency texture layer and a low-frequency illumination layer through a multi-scale residual network; acquiring illumination intensity, color temperature and scene categories in real time by using an ambient light sensor and a scene semantic segmentation model, and generating dynamic compensation parameters; carrying out dynamic range expansion on a low-frequency illumination layer based on a physical illumination model, and adjusting the weight of highlight suppression and dark area enhancement through a self-adaptive S-shaped exposure curve; a double-branch generative adversarial network is adopted, noise suppression and super-resolution reconstruction are carried out on the high-frequency layer, and texture detail enhancement is carried out on the intermediate-frequency layer; aligning the data of the depth camera and the infrared sensor with the visible light image through a cross-modal fusion module; and performing tone mapping on the fused image based on human visual characteristics, and outputting an enhanced image with a high dynamic range and reserved details.

The invention provides a pixel dynamic calibration method and device for a display, equipment and a storage medium. The method comprises the following steps: acquiring display parameters and a calibration image of the display; performing visual semantic analysis on the calibration image to generate a partition guidance mask, and marking a plurality of areas with different visual fidelity in the image by the partition guidance mask; generating a group of parallel region tone mapping curves for the plurality of regions based on the display parameters and the partition guide mask; performing synchronous processing on a corresponding region of the calibration image by using the region tone mapping curve to generate a partition mapping result, and fusing the partition mapping result into a correction image; generating a strategy execution record based on the partition guidance mask and the regional tone mapping curve; binding the strategy execution record with the content characteristics of the calibration image, and storing as a scene calibration strategy file; and when a new image frame is processed, calling the matched scene calibration strategy file for processing.

To employ low resolution, noisy tone mapping operations for high resolution images, at least one raw image frame is converted to a first image at a higher resolution and a second image at a lower resolution. Tone mapping is applied to the second image to derive a third image at the lower resolution. Histogram matching and regularization are performed to determine a lookup table approximating histogram matching of the second image to the third image. A global gain map is derived based on luma for the first image and the lookup table. A local gain map is derived by up-sampling and denoising residual differences between the third image and the lookup table applied to the second image. Based on the global gain map and the local gain map, a total gain map is determined for tone mapping the first image to produce a fourth image at the first resolution.

A method includes receiving a quantized video having a first maximum luminance level or brightness associated with a mastering display with which the quantized video was mastered. The method also includes de-quantizing the quantized video in order to generate a de-quantized video. The method further includes applying a scene-adaptive tone mapping function to the de-quantized video in order to generate a tone mapped video. In addition, the method includes displaying the tone mapped video on a target display. The tone mapped video has a second maximum luminance level or brightness associated with the target display, and the second maximum luminance level or brightness is less than the first maximum luminance level or brightness.

The invention discloses an HDR dynamic tone mapping method and system. The HDR dynamic tone mapping method comprises the following steps: S1, acquiring an ambient light parameter, a user interaction parameter and a display equipment state parameter which are acquired in real time; s2, performing dynamic parameter fusion on the ambient light parameters, the user interaction parameters, the display equipment state parameters and video content metadata to generate dynamic metadata; s3, generating a self-adaptive tone mapping curve based on the dynamic metadata, wherein the self-adaptive tone mapping curve adjusts a brightness mapping relation through an equipment aging compensation parameter; and S4, measuring the error between the actual display image quality and the theoretical value, and correcting the compensation parameter in the dynamic parameter fusion according to the error value. According to the method, various parameters are collected in real time, the adaptive tone mapping curve is generated through dynamic fusion, and errors are corrected in combination with closed-loop feedback, so that the problem of image quality degradation caused by environment change, equipment aging and user interaction difference in the traditional HDR technology is solved, and high-precision and adaptive dynamic display optimization is realized.

The invention relates to the technical field of image processing, in particular to an image data desensitization method, device and equipment, and the method comprises the steps: extracting a to-be-processed image or a RAW domain image of a to-be-processed video stream; sequentially performing wide dynamic range processing, first Bayer noise processing and tone mapping processing on the RAW domain image to obtain a first processed image; obtaining a dynamic ROI detection model and a privacy grading model; based on the first processing image and the dynamic ROI detection model, a second processing image is output, and the second processing image is that a privacy area is marked on the first processing image; based on the second processing image and a privacy grading model, obtaining a privacy level comprehensive score of each privacy area; and determining a corresponding desensitization means based on the privacy level comprehensive score of each privacy area so as to carry out pixel level privacy processing on the second processing image, and realizing end-to-end security privacy protection by processing the RAW domain image of the video or the image.

This disclosure provides a tone mapping method and apparatus. In the method, after global tone mapping is performed on a to-be-displayed image, local mapping information is adjusted to obtain the adjusted local mapping information; and based on the adjusted local mapping information, local tone mapping is performed on at least some pixels in the to-be-displayed image on which global tone mapping is performed. In embodiments of this disclosure, a global and local joint tone mapping solution is used, and local mapping is performed based on the adjusted local mapping information, to balance an uncoordinated contrast between different regions in local tone mapping, and effectively improve tone mapping effect and display effect of an image.

The invention provides an image processing method, and the method comprises the steps: carrying out the conversion processing of a to-be-processed YUV image in a first color gamut range, obtaining an RGB image in a second color gamut range, generating a target mapping function, and enabling the target mapping function to be a function obtained through the fusion processing of a first mapping function and a second mapping function, the first mapping function is a function obtained by performing histogram statistics according to a Y channel component of the to-be-processed YUV image, and the second mapping function is a preset function, and performing mapping processing on an image in the to-be-played video based on the target mapping function to obtain a target RGB image. According to the scheme, the RGB pixels are combined with the brightness, the brightness of the image after tone mapping is increased, and the image quality of the image is improved.

Disclosed is a method for enabling exposure-guided three-dimensional (3D) reconstruction, including (i) receiving Low Dynamic Range (LDR) input image captured by camera; (ii) rendering High Dynamic Range (HDR) image corresponding to input image, using HDR 3D reconstruction model pre-trained for HDR image reconstruction of 3D environment; (iii) applying HDR to LDR tone-mapping operator on HDR image, for producing tone-mapped LDR image; (iv) determining first loss function (FLF) between input image and tone-mapped LDR image, FLF comprising weighted pixel value differences between pixels of input image and corresponding pixels of tone-mapped LDR image; (v) determining whether input image has saturated pixel(s), saturated pixel(s) comprises: highlight saturated pixel, shadow saturated pixel; (vi) de-weighting pixel value difference corresponding to saturated pixel in FLF; (vii) back-propagating gradient of FLF with respect to model parameters, through differentiable render function of HDR 3D reconstruction model, for adjusting model parameters in way that reduces FLF.

The invention discloses a night enhanced imaging and dynamic denoising method for an automobile data recorder, relates to the technical field of vehicle-mounted image processing and computational photography, and is used for solving the problems of insufficient brightness and too strong noise of night videos of the automobile data recorder under a low-illumination condition. Estimating the zero-mean Gaussian noise intensity of a read link and the Poisson noise intensity increasing along with the brightness in the same frame, converting the zero-mean Gaussian noise intensity and the Poisson noise intensity into brightness equivalent parameters, and introducing a unified control function G as the scale reference of all enhancement and noise reduction links; defining a sharing priori H and carrying out unified constraint in dense optical flow, depth time sequence denoising and local tone mapping; and in combination with the motion mask and the background model, performing differential space-time denoising and proportional write-back, and in cooperation with motion blur detection, spatial variation motion kernel and constrained deconvolution and multi-frame detail recharge, obtaining target brightness and outputting an RGB frame after proportional write-back.

The invention discloses a self-adaptive high-dynamic-range image generation method in a chemical monitoring scene, and belongs to the technical field of high-dynamic imaging and computational imaging. Performing registration preprocessing on the acquired reference image based on a brightness consistency criterion; constructing a high dynamic range image generation network model, inputting the reference image into the model, performing feature extraction and fusion through a multi-scale network, and generating a high dynamic range image based on the fused features; performing tone mapping on the generated high dynamic range image based on a brightness consistency criterion; and comparing the generated high dynamic range image with a reference image, calculating a pixel-level loss function and multi-dimensional perception loss, and optimizing an image generation process through a back propagation training network model. According to the method, imaging details of different scales are captured through a multi-scale feature processing method, so that the generated image is better in brightness range and details, and the expressive force of the image under a complex illumination condition is ensured.

A computing system for generating a gain map-based enhanced High Dynamic Resolution (HDR) image receives an HDR image comprising a plurality of pixels, each pixel having one or a plurality of brightness values for each of a plurality of color components, applies at least a first tone mapping algorithm to each pixel in the HDR image, generates a gain map using the HDR image and the SDR image, generates a gain map-based enhanced HDR image based on the SDR image and the gain map, and generates an output based on the gain map-based enhanced HDR image.

The invention relates to the technical field of augmented reality, in particular to a 24-solar-term astronomical space-time presentation method and system based on mixed reality. The method comprises the following steps: firstly, reading augmented reality scene initialization data, configuring virtual scene parameters, and executing three-dimensional scene registration to generate a registration matrix; executing visual tracking by collecting an image stream, and generating a viewpoint transformation matrix; the system performs real-time sky semantic segmentation on an image stream to generate a binarized sky mask, and constructs an augmented reality rendering pipeline: synthesizing registration and viewpoint matrix calculation rendering operators, using the sky mask as an Alpha mask to perform pixel-level fusion of a virtual starry sky and a real sky, and combining sparse point clouds to perform depth occlusion synthesis, so as to obtain an augmented reality rendering pipeline. An atmospheric optical coloring model and a dynamic volume particle system are loaded for environmental atmosphere enhancement; and optical consistency fusion of a virtual image and a real environment is further realized through HDR luminosity alignment and tone mapping, and finally high-fidelity augmented reality superposition is realized.

The embodiment of the invention provides an image processing method, electronic equipment, a storage medium and a program product. The image processing method comprises the following steps: determining the original pixel brightness of a current image according to image data to be processed; dividing the original pixel brightness into a plurality of data branches; obtaining a histogram corresponding to the original pixel brightness of each data branch; determining a tone mapping curve of each data branch based on a tone mapping model and the histogram; fusing the tone mapping curve of each data branch to obtain a fusion curve; obtaining target pixel brightness corresponding to the original pixel brightness based on the fusion curve; and determining target image data corresponding to the to-be-processed image data based on the original pixel brightness and the target pixel brightness. According to the scheme of the embodiment, automatic tone mapping is realized, and the flexibility and the adaptability of tone mapping are improved.

The invention belongs to the technical field of image processing, and particularly relates to a wide dynamic image fusion method and device for a fast moving scene. A single-lens double-light-path light splitting method is adopted, optical systems with the same type of sensors, the same exposure duration and different aperture coefficients are adopted for double light paths, field angles are matched, scenes are the same, and the error is smaller than 0.5 pixel; the method comprises the following steps: performing video image acquisition, performing wavelet transform on acquired two paths of image data, decomposing two paths of image matrixes to obtain a high-frequency detail image and a low-frequency-width dynamic image, and performing multi-depth-of-field fusion on the high-frequency detail image; performing multi-exposure fusion on the low-frequency wide dynamic image to generate HDR wide dynamic data, and performing tone mapping to form an LDR low-frequency image; and combining the high-frequency fusion detail image and the LDR low-frequency image. According to the method, the image without overexposure, with large depth of field and multiple details can be obtained, and the effects of video processing tasks such as target searching and tracking are effectively improved.

The invention discloses a low-illumination image enhancement method based on semantic perception and differentiable tone mapping, and belongs to the field of computer vision and image processing. According to the method, semantic information of each region in an image is extracted through a semantic segmentation network, different importance weights are distributed for different semantic regions, and then a differentiable tone mapping curve generation module is driven to dynamically adjust brightness and contrast enhancement parameters of each region. According to the system, an end-to-end trainable architecture is adopted, semantic perception loss, physical consistency loss and image quality loss are jointly optimized, and finally content self-adaptive enhancement of low-illumination images is achieved. Compared with the prior art, the problems of semantic information loss, overexposure or insufficient enhancement and the like in a traditional method are effectively solved. By introducing semantic perception driven by deep learning and differentiable tone mapping, the detail and color consistency of a semantic region can be more accurately kept in the image enhancement process. In the aspect of performance evaluation, the peak signal-to-noise ratio (PSNR) of the method is improved by more than 3.2 dB, the average intersection-to-union ratio (mIOU) of semantic segmentation is improved by more than 8.5%, and the method is remarkably superior to an existing mainstream image enhancement method.

The embodiment of the invention relates to the technical field of terminals, in particular to a method for generating an HDR image and electronic equipment, and can improve the display effect of the HDR image. The method comprises the following steps: acquiring a first HDR image, and performing tone mapping on the first HDR image to obtain a second HDR image; the first HDR image comprises a first highlight area, and the first highlight area comprises a highlight object; the second HDR image comprises a second highlight area, and the second highlight area corresponds to the first highlight area; correcting the gradient direction of the first pixel in the second highlight area into the gradient direction of the second pixel in the first highlight area to obtain a third HDR image; the second pixel corresponds to the first pixel; wherein the gradient direction of one pixel is positive and negative of the difference value between the brightness value of the next pixel of the pixel on a first direction axis and the brightness value of the pixel, and the first direction axis comprises an x axis and a y axis; wherein the dynamic imaging range of the third HDR image is smaller than that of the first HDR image, and the third HDR image is used for displaying.

This disclosure provides systems, methods, and devices for machine learning techniques that support image processing for use in a vehicle assistance system. In one aspect, a method is provided that includes receiving a first image frame captured from a camera positioned on a vehicle. The method further includes determining, based on the first image frame, a probability value that the first image frame depicts at least a portion of a windshield wiper blade. A time filter is determined based on the probability value, and an output image frame is determined by tone mapping a second image frame according to the time filter. Other aspects and features are also claimed and described.

In some examples, the method for tone mapping a high dynamic range (HDR) image to a lower dynamic range image (TDR) comprises obtaining a luminous intensity image based on the HDR image, processing the luminous intensity image using a feature extractor network, whereby to generate a feature map, processing the feature map using at least one neural network module of multiple neural network modules, obtaining a tone mapping operator based on an output of the at least one neural network module of the multiple neural network modules, and applying the tone mapping operator to the HDR image, whereby to obtain the TDR image, wherein the tone mapping operator comprises a tone mapping curve.

A video encoding device may determine whether to apply neural-network post-filter (NNPF) for tone mapping. The device may, based on a determination to apply NNPF, obtain at least one metadata parameter associated with NNPF tone mapping. The device may include, in video data, a neural-network post-filter tone mapping indication that NNPF for tone mapping is to be applied. A video decoding device may determine whether to apply NNPF for tone mapping based on a neural-network post-filter tone mapping indication. The device may, based on a determination to apply NNPF, determine at least one metadata parameter associated with NNPF tone mapping. The device may apply NNPF for tone mapping based on the at least one metadata parameter. The device may obtain an NNPF characteristics (NNPFC) tone mapping sub-purpose indication. The at least one metadata parameter associated with NNPF tone mapping may be determined based on the NNPFC tone mapping sub-purpose indication.

The invention relates to a tone mapping method and device, electronic equipment and a storage medium. According to the method, a first logical operation unit, a second logical operation unit, a third logical operation unit and a lookup table of a field programmable logic gate array are matched with one another. Specifically, by inputting the Y channel median value into the lookup table, the Y channel value adjustment coefficient can be directly obtained, and exponential operation between the Y channel median value and the Y channel value adjustment coefficient does not need to be carried out. By inputting the ratio of the Y channel value of each pixel stretched to the full domain to the median value of the Y channel of each pixel stretched to the full domain into the lookup table, the compression value of the Y channel can be directly obtained, and exponential operation of the ratio and the compression value of the Y channel is not needed, so that the data processing efficiency is improved, and the operation resources are saved.

The invention provides a halo suppression method and device during tone mapping, equipment, a medium and a product, and relates to the technical field of image processing. The halo suppression method during tone mapping comprises the following steps: acquiring a dynamic range compression curve of an image to be processed; calculating the target probability of each pixel point based on the pixel value of each pixel point in the to-be-processed image; the target probability represents the probability of whether the pixel point belongs to halo; based on the target probability of each pixel point, correcting the initial brightness value of the pixel point to obtain an updated brightness value of each pixel point; wherein the probability that the pixel point belongs to the halo is positively correlated with the amplification of the updated brightness value obtained by correction relative to the initial brightness value; and determining a respective mapping brightness value from the dynamic range compression curve based on the updated brightness value of each pixel point to obtain an output image.

Provided is an electronic device for, and method of, displaying an image, the electronic device including: a display; at least one processor; and memory storing one or more instructions that, when individually or collectively executed by the at least one processor, may cause the electronic device to: obtain an on-pixel ratio (OPR) based on input image data, determine a target luminance based on the OPR and a display set luminance, perform HDR tone mapping, using the target luminance, on the input image data, and control the display to display an image corresponding to the input image data on which HDR tone mapping is performed.

One embodiment provides a method comprising determining multi-dimensional metadata corresponding to an input image, and determining ambient light information indicative of an ambient light level in a surrounding environment of a display device. The multi-dimensional metadata includes a distribution function of pixels in the input image. The method further comprises determining one or more gains to adaptively compensate for the ambient light level in the surrounding environment based on the ambient light information. The method further comprises generating a tone mapping function based on the multi-dimensional metadata and the one or more gains, and applying the tone mapping function to the input image to generate a tone mapped image that is adaptively compensated for the ambient light level in the surrounding environment. The tone mapped image is provided to the display device for presentation.

This application provides a high dynamic range HDR video processing method, an encoding device, and a decoding device. The method includes: obtaining dynamic metadata of an Nth HDR video frame according to a dynamic metadata generation algorithm; calculating a tone-mapping (tone-mapping) curve parameter of the Nth HDR video frame based on the dynamic metadata of the Nth HDR video frame; generating a tone-mapping curve based on the curve parameter; determining, according to a quality assessment algorithm, distortion D′ caused by the tone-mapping curve; comparing D′ and DT, to determine a mode used by the Nth HDR video frame, where the mode is an automatic mode or a director mode, and DT is a threshold value; and determining metadata of the Nth HDR video frame based on the determined mode used by the Nth HDR video frame.

The application discloses a tone mapping method and device and a computer storage medium. The method comprises the following steps: acquiring first image data corresponding to a video image, and determining second image data corresponding to the video image based on a first mapping relationship and the first image data; wherein the first mapping relationship is used for electro-optical conversion and tone mapping; the video image is an HDR image; performing color gamut conversion based on the second image data to obtain third image data corresponding to the video image; and determining a tone-mapped image corresponding to the video image based on a second mapping relationship and the third image data; wherein the second mapping relationship is used for photoelectric conversion; and the tone-mapped image is an SDR image.

The application discloses a method and related device for image processing, obtaining a first feature map and a second feature map, the first feature map is used for describing high-frequency detail features of a target image, and the second feature map is used for describing low-frequency structural features of the target image, and the first feature map and the second feature map have the same size. The first feature map is subjected to first convolution processing to obtain a first enhancement result, and the second feature map is subjected to second convolution processing to obtain a second enhancement result. The first enhancement result and the second enhancement result are fused to obtain a first fusion result, and the first fusion result is used for generating an enhanced image of the target image. In the application, the high-frequency detail features and the low-frequency structural features of the target image are subjected to convolution processing respectively, wherein the convolution processing of the high-frequency detail features can optimize the detail features of the image, the convolution processing of the low-frequency structural features can optimize the tone mapping of the image, and through the fusion of the two different types of convolution results, the quality of image enhancement can be improved.

The application discloses a tone mapping method and system based on a lookup table and a Laplace filter, and belongs to the technical field of image processing.The input image is first decomposed into an adaptive Laplace pyramid;then a low-frequency image at the bottom layer of the adaptive Laplace pyramid is input into a weight predictor to obtain a pixel-level weight map, and a three-dimensional lookup table is used to perform three-linear interpolation on the low-frequency image to obtain a preliminary mapping image; then the preliminary mapping image and the weight map are fused pixel by pixel to generate an image at the bottom layer of the fine-tuned Laplace pyramid; then a filter parameter prediction module is used to learn a parameter value map of the remaining layer images of the adaptive Laplace pyramid, and the parameter value map is applied to a local Laplace filter to obtain the remaining layer images of the fine-tuned Laplace pyramid; finally, the fine-tuned Laplace pyramid is reconstructed to obtain a tone-mapped image.The application can retain local edge details of an image while performing global tone mapping.

Various implementations provide unvarnished video based on adjusting camera parameters according to environmental modeling. Environmental characteristics may be determined based on modeling a physical environment from sensor data captured via one or more sensors. For example, this may involve determining ambient light source optical characteristics, ambient surface optical characteristics, 3D mapping of the environment, user behavior, prediction of optical characteristics of light entering the camera, and the like. The method may involve determining camera parameters of an image captured via an image sensor based on environmental characteristics. For example, the method may determine exposure, gain, tone mapping, color balance, noise reduction, sharpness enhancement. The method may determine camera parameters based on user information (e.g., user preferences, user activity, etc.). The method may involve providing a transparent video of the physical environment based on the determined camera parameters.

The present invention relates generally to the field of video processing, and more specifically to high dynamic range (HDR) video and image processing. In particular, the present invention relates to determining one or more curve parameters of a tone mapping curve. For example, a device (encoder or decoder) can obtain a high dynamic range (HDR) video frame and metadata associated with the HDR video frame. The device can also obtain a pair of anchor points from the HDR video frame and the metadata. The pair of anchor points includes a first anchor point and a second anchor point of the tone mapping curve. Furthermore, the device can generate the one or more curve parameters of the tone mapping curve from the pair of anchor points.