Abstract: A method includes receiving an input image and generating a target image using the input image. Generating the target image includes, for each tile of a plurality of tiles of the input image, processing the tile to obtain an incoming tile, modifying the incoming tile by applying scaling and offset coefficients, for each pixel in the target image that overlaps with a previous tile in the target image, updating the pixel in the target image with a combination of a pixel value of the pixel in the target image and a pixel value of a first corresponding pixel from the modified incoming tile, and for each pixel in the target image that corresponds to the tile and that does not overlap with the previous tile, updating the target image by filling in each such pixel in the target image with a second corresponding pixel from the modified incoming tile.

Abstract: A method includes converting each of multiple image frames at a first exposure level to YUV image frames and to RGB image frames. The method also includes generating aligned color filter array images using the RGB image frames. The method also includes generating, by a first artificial intelligence model, a single-frame blended RGB image at the first exposure level. The method also includes generating a single-frame blended negative color filter array image using aligned negative color filter array images, wherein the aligned negative color filter array images are generated using multiple negative image frames at various exposure levels. The method also includes generating, by a second artificial intelligence model using the single-frame blended negative color filter array image, a single-frame blended negative RGB image. The method also includes blending the single-frame blended RGB image at the first exposure level and the single-frame blended negative RGB image.

Abstract: A method includes obtaining multiple input image frames and generating bad pixel maps associated with different ones of the input image frames. Each bad pixel map is generated using first and second adaptive thresholds that are based on statistical properties of image data contained in a specified operation window within the associated input image frame. The method also includes generating at least one refined bad pixel map using the bad pixel maps associated with two or more of the input image frames. The method further includes using one or more coordinates of one or more bad pixels identified in the at least one refined bad pixel map to update one or more pixel values of at least one of the input image frames.

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, 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 input image frames, including at least two captured using different capture conditions, 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 also includes combining the bad pixel maps and performing a morphological operation to refine the combined bad pixel map and 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 multiple input image frames and generating a high dynamic range (HDR) blended image based on the input image frames, where the HDR blended image has a higher dynamic range than individual ones of the input image frames. The method also includes performing a tone fusion operation on the HDR blended image based on a semantic delta-weight map to generate a fused image. Performing the tone fusion operation includes synthesizing multiple low dynamic range (LDR) images based on the HDR blended image and generating initial weight maps based on the LDR images. Performing the tone fusion operation also includes generating filtered weight maps based on the initial weight maps, the semantic delta-weight map, and a guided filter. Performing the tone fusion operation further includes generating the fused image based on the filtered weight maps and decomposed versions of the LDR images.

Abstract: A method includes generating alignment maps for a first image frame having a first exposure level and a second image frame having a second exposure level different than the first exposure level. The method also includes generating, for the second image frame and a third image frame having a third exposure level different than the first and second exposure levels, shadow maps, saturation maps, and multi-exposure (ME) motion maps based on the alignment maps. The method further includes determining, based on the shadow maps, saturation maps, and ME motion maps, whether to perform machine learning-based denoising and, if so, on which image frame(s) to perform the machine learning-based denoising. In addition, the method includes updating at least one saturation map and at least one ME motion map for at least one of the second and third image frames depending on the image frame(s) on which the denoising is to be performed.

Abstract: A method includes obtaining multiple input image frames and generating bad pixel maps associated with different ones of the input image frames. Each bad pixel map is generated using first and second adaptive thresholds that are based on statistical properties of image data contained in a specified operation window within the associated input image frame. The method also includes generating at least one refined bad pixel map using the bad pixel maps associated with two or more of the input image frames. The method further includes using one or more coordinates of one or more bad pixels identified in the at least one refined bad pixel map to update one or more pixel values of at least one of the input image frames.

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: An electronic device includes a processor configured to estimate green values at red and blue pixel locations of an input Bayer frame based on green values at green pixel locations of the input Bayer frame. The processor is also configured to generate red, green, and blue channels of joint demosaiced-warped output RGB pixels from the input Bayer frame based on the green values at the green pixel locations, the estimated green values at the red and blue pixel locations, an alignment vector map, and kernels for red, green, and blue pixels.

Abstract: A method includes obtaining multiple input image frames and generating a high dynamic range (HDR) blended image based on the input image frames, where the HIDR blended image has a higher dynamic range than individual ones of the input image frames. The method also includes performing a tone fusion operation on the HIDR blended image based on a semantic delta-weight map to generate a fused image. Performing the tone fusion operation includes synthesizing multiple low dynamic range (LDR) images based on the HIDR blended image and generating initial weight maps based on the LDR images. Performing the tone fusion operation also includes generating filtered weight maps based on the initial weight maps, the semantic delta-weight map, and a guided filter. Performing the tone fusion operation further includes generating the fused image based on the filtered weight maps and decomposed versions of the LDR images.

Abstract: A method includes generating alignment maps for a first image frame having a first exposure level and a second image frame having a second exposure level different than the first exposure level. The method also includes generating, for the second image frame and a third image frame having a third exposure level different than the first and second exposure levels, shadow maps, saturation maps, and multi-exposure (ME) motion maps based on the alignment maps. The method further includes determining, based on the shadow maps, saturation maps, and ME motion maps, whether to perform machine learning-based denoising and, if so, on which image frame(s) to perform the machine learning-based denoising. In addition, the method includes updating at least one saturation map and at least one ME motion map for at least one of the second and third image frames depending on the image frame(s) on which the denoising is to be performed.

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: An electronic device includes a processor configured to estimate green values at red and blue pixel locations of an input Bayer frame based on green values at green pixel locations of the input Bayer frame. The processor is also configured to generate red, green, and blue channels of joint demosaiced-warped output RGB pixels from the input Bayer frame based on the green values at the green pixel locations, the estimated green values at the red and blue pixel locations, an alignment vector map, and kernels for red, green, and blue pixels.

Abstract: The present disclosure describes devices and methods for generating RGB images from Bayer filter images using adaptive sub-pixel spatiotemporal interpolation. An electronic device includes a processor configured to estimate green values at red and blue pixel locations of an input Bayer frame based on green values at green pixel locations of the input Bayer frame and a kernel for green pixels, generate a green channel of a joint demosaiced-warped output RGB pixel from the input Bayer frame based on the green values at the green pixel locations, the kernel for green pixels, and an alignment vector map, and generate red and blue channels of the joint demosaiced-warped output RGB pixel from the input Bayer frame based on the estimated green values at the red and blue pixel locations, kernels for red and blue pixels, and the alignment vector map.

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: The present disclosure describes devices and methods for generating RGB images from Bayer filter images using adaptive sub-pixel spatiotemporal interpolation. An electronic device includes a processor configured to estimate green values at red and blue pixel locations of an input Bayer frame based on green values at green pixel locations of the input Bayer frame and a kernel for green pixels, generate a green channel of a joint demosaiced-warped output RGB pixel from the input Bayer frame based on the green values at the green pixel locations, the kernel for green pixels, and an alignment vector map, and generate red and blue channels of the joint demosaiced-warped output RGB pixel from the input Bayer frame based on the estimated green values at the red and blue pixel locations, kernels for red and blue pixels, and the alignment vector map.