Abstract: A method includes obtaining a blended red-green-blue (RGB) image frame of a scene. The method also includes performing, using at least one processing device of an electronic device, an interband denoising operation to remove at least one of noise and one or more artifacts from the blended RGB image frame in order to produce a denoised RGB image frame. Performing the interband denoising operation includes performing filtering of red, green, and blue color channels of the blended RGB image frame to remove at least one of the noise and the one or more artifacts from the blended RGB image frame. The filtering of the red and blue color channels of the blended RGB image frame is based on image data of at least one of the green color channel and a white color channel of the blended RGB image frame.

Abstract: An apparatus includes a memory configured to store images and a processor. The processor is configured to receive an input image. The processor is further configured to partition a human mask in the input image using a segmentation algorithm. The processor is also configured to generate a skin map based on identifying skin in the input image using the human mask. In addition, the processor is configured to process an output image with brightening applied using the skin map.

Abstract: A method includes obtaining multiple image frames. The method also includes selecting, using at least one processing device of an electronic device, an asymmetrical image pair from the multiple image frames. The asymmetrical image pair includes a first image frame and a second image frame, where the first image frame has a shorter exposure than the second image frame. The method further includes identifying, using the at least one processing device, one or more features based on the asymmetrical image pair. The method also includes determining, using the at least one processing device, whether the first image frame contains flicker based on the one or more features. In addition, the method includes enabling or disabling, using the at least one processing device, the first image frame as a reference candidate based on the determination whether the first image frame contains flicker.

Abstract: A method includes obtaining a ground truth image and generating multiple image frames using the ground truth image, a modeled optical blur, and a modeled global motion. The method also includes generating multiple mosaic image frames using the image frames and a color filter array and generating multiple raw input image frames using the mosaic image frames and a noise model associated with at least one imaging sensor. The method further includes providing the raw input image frames to a multi-frame processing pipeline in order to generate synthetic training data. In addition, the method includes training a machine learning-based image processing engine using the ground truth image and the synthetic training data.

Abstract: A method includes extracting multiple shallow features from a low-resolution image using a shallow feature extractor that includes a quaternion convolutional network. The method also includes extracting multiple deep features from the multiple shallow features using a deep feature extractor that includes multiple quaternion residual distillation blocks (QRDBs), where each QRDB includes a quaternion self-attention module. The method further includes reconstructing the multiple deep features into a high-resolution image. Each QRDB may further include a quaternion gated deconvolutional feed forward network (QGDFN) configured to suppress one or more of the multiple deep features.

Abstract: A method includes obtaining, using at least one processing device of an electronic device, an input image containing blur. The method also includes generating, using the at least one processing device, an edge enhancement mask and a gain mask based on the input image. The method further includes generating, using the at least one processing device, a halo-suppressed edge mask based on the edge enhancement mask and the gain mask. In addition, the method includes generating, using the at least one processing device, a sharpened image based on the input image and the halo-suppressed edge mask.

Abstract: A method includes obtaining, using at least one image sensor of an electronic device, a first image frame and multiple second image frames of a scene. Each of the second image frames has an exposure time different from an exposure time of the first image frame. The method also includes generating, using at least one processor, blur kernels indicating a motion direction of the first image frame using an optical flow network. The method further includes refining, using the at least one processor, the blur kernels using a convolutional neural network. In addition, the method includes generating, using the at least one processor, a target image frame of the scene using the refined blur kernels and occlusion masks for the second image frames.

Abstract: A method includes obtaining multiple input image frames and determining how to warp at least one of the input image frames. The method also includes performing an intraband demosaic-warp operation to reconstruct image data in different color channels of the input image frames and warp the at least one input image frame to produce RGB input image frames. The method further includes blending the RGB input image frames to produce a blended RGB image frame, performing an interband denoising operation to produce a denoised RGB image frame, and performing an interband sharpening operation to produce a sharpened RGB image frame. In addition, the method includes performing an interband demosaic operation to substantially equalize high-frequency content in different color channels of the sharpened RGB image frame to produce an equalized sharpened RGB image frame and generating a final image of the scene based on the equalized sharpened RGB image frame.

Abstract: A method includes obtaining multiple images of a scene using at least one red-green-blue-white (RGBW) image sensor. The method also includes generating multi-channel frames at different exposure levels from the images. The method further includes estimating motion across exposure differences between the different exposure levels using a white channel of the multi-channel frames as a guidance signal to generate multiple motion maps. The method also includes estimating saturation across the exposure differences between the different exposure levels to generate multiple saturation maps. The method further includes using the generated motion maps and saturation maps to recover saturations from the different exposure levels and generate a saturation-free RGBW frame. In addition, the method includes processing the saturation-free RGBW frame to generate a final image of the scene.

Abstract: A method includes obtaining multiple image frames captured using at least one imaging sensor. The method also includes generating a local tone map, a global tone map look-up table (LUT), and one or more contrast enhancement LUTs based on at least one of the image frames and one or more parameters of the at least one imaging sensor. The method further includes generating a blended and demosaiced image based on the image frames and generating a local tone mapped image based on the blended and demosaiced image and the local tone map. The method also includes adjusting color saturation based on the local tone mapped image to generate a corrected image. In addition, the method includes generating an output image based on the corrected image, the global tone map LUT, and the one or more contrast enhancement LUTs.

Abstract: A method includes obtaining input image frames, including at least two captured using different capture conditions. The method also includes separating color channels of each image frame and generating at least one bad pixel map for each color channel of each image frame. Each bad pixel map is generated by identifying one or more outliers in pixel values in the color channel based on an intensity distribution of pixel values in an operation window within the color channel. The operation window has a window size based on the capture condition and/or local image content in the corresponding image frame. The method further includes combining the bad pixel maps and performing a morphological operation to refine the combined bad pixel map. In addition, the method includes using one or more coordinates of one or more bad pixels in the refined bad pixel map to update one or more pixel values of at least one image frame.

Abstract: A method includes obtaining a raw image in a first image domain. The method also includes determining a color distribution and an amount of variation in the raw image. The method further includes using an iterative process to generate a dead leaf image from a blank image in the first image domain. The iterative process includes adding multiple circles and multiple sticks to the blank image until the dead leaf image is filled. The iterative process also includes blurring portions of the dead leaf image during at least one iteration of the iterative process. Textures of the multiple circles are blended based on the color distribution and the amount of variation in the raw image.

Abstract: A method includes dividing an image into overlapping image patches each having a specified size. The method also includes analyzing content of each image patch using a mathematical transform technique to classify each image patch into at least one class. The method further includes filtering each image patch for noise suppression by suppressing one or more transform coefficients of the image patch. An amount of suppression for each of the one or more transform coefficients is selected according to the at least one class of the image patch. In addition, the method includes reconstructing the filtered image patches into an output image.

Abstract: Various image sharpening techniques are disclosed. For example, a method for image sharpening includes obtaining, using at least one sensor of an electronic device, an image that includes visual content. The method also includes generating an edge map that indicates edges of the visual content within the image. The method further includes applying a high-pass signal and an adaptive gain based on the edge map to sharpen the image. The method also includes generating a bright halo mask and a dark halo mask based on the edge map, where the bright halo mask indicates an upper sharpening limit and the dark halo mask indicates a lower sharpening limit. In addition, the method includes modifying a level of sharpening at one or more of the edges within the sharpened image to provide halo artifact reduction based on the bright halo mask and the dark halo mask.

Abstract: A method includes obtaining multiple image frames. The method also includes selecting, using at least one processing device of an electronic device, an asymmetrical image pair from the multiple image frames. The asymmetrical image pair includes a first image frame and a second image frame, where the first image frame has a shorter exposure than the second image frame. The method further includes identifying, using the at least one processing device, one or more features based on the asymmetrical image pair. The method also includes determining, using the at least one processing device, whether the first image frame contains flicker based on the one or more features. In addition, the method includes enabling or disabling, using the at least one processing device, the first image frame as a reference candidate based on the determination whether the first image frame contains flicker.

Abstract: A method includes filtering an input image through a discrete cosine transform based noise filter (DCT-NF). The DCT-NF converts the input image from an original space into a perceptual space, applying gamma correction. The DCT-NF separates luminance channels of the input image from chroma channels of the input image. The DCT-NF divides the input image into overlapping patches and computes DCT transform of the patches. Each patch is a different partial portion of the input image. The DCT-NF suppresses patches that include an input DCT coefficient within a threshold range. The DCT-NF applies an inverse discrete cosine transform (IDCT) to the suppressed patches and remaining overlapping patches that include an input DCT coefficient outside the threshold range. The DCT-NF re-combines luminance and chroma channels of the IDCT-transformed patches. The DCT-NF generates a DCT noise-filtered output image by re-converting the IDCT-transformed patches to the original space by applying inverse gamma correction.

Abstract: A method for training data generation includes obtaining a first set of image frames of a scene and a second set of image frames of the scene using multiple exposure settings. The method also includes generating an alignment map, a blending map, and an input image using the first set of image frames. The method further includes generating a ground truth image using the alignment map, the blending map, and the second set of image frames. In addition, the method includes using the ground truth image and the input image as an image pair in a training dataset when training a machine learning model to reduce image distortion and noise.

Abstract: A method includes obtaining an image and a gain map associated with the image. The method also includes identifying image patches in the image and corresponding gain map patches in the gain map. Different image patches are centered around different anchor points in the image. The method further includes, for each image patch and its corresponding gain map patch, generating an intensity-gain curve for the associated anchor point. The intensity-gain curve specifies (i) gain values based on the corresponding gain map patch for intensity values up to a threshold intensity value and (ii) gain values based on one or more input parameters for intensity values above the threshold intensity value. In addition, the method includes combining the intensity-gain curves to generate a 3D lookup table, which identifies the gain values for the anchor points in the image at each of multiple intensity values.

Abstract: An apparatus includes a memory configured to store images and a processor. The processor is configured to receive an input image. The processor is further configured to partition a human mask in the input image using a segmentation algorithm. The processor is also configured to generate a skin map based on identifying skin in the input image using the human mask. In addition, the processor is configured to process an output image with brightening applied using the skin map.

Abstract: An electronic device includes at least one imaging sensor and at least one processor coupled to the at least one imaging sensor. The at least one imaging sensor is configured to capture a burst of image frames. The at least one processor is configured to generate a low-resolution image from the burst of image frames. The at least one processor is also configured to estimate a blur kernel based on the burst of image frames. The at least one processor is further configured to perform deconvolution on the low-resolution image using the blur kernel to generate a deconvolved image. In addition, the at least one processor is configured to generate a high-resolution image using super resolution (SR) on the deconvolved image.