Abstract: An image capture device includes an image sensor and a processor. The image sensor is configured to capture a first plurality of frames, a second plurality of frames, and a third plurality of frames. The processor includes a first denoising layer and a second denoising layer. The first denoising layer includes a first denoiser, a second denoiser, and a third denoiser. The first denoiser is configured to denoise the first plurality of frames and output a first denoised frame. The second denoiser is configured to denoise the second plurality of frames and output a second denoised frame. The third denoiser is configured to denoise the third plurality of frames and output a third denoised frame. The second denoising layer includes a fourth denoiser. The fourth denoiser is configured to output a denoised frame based on the first denoised frame, the second denoised frame, and the third denoised frame.

Abstract: An image capture device includes an image sensor and a processor. The image sensor is configured to capture a first plurality of frames, a second plurality of frames, and a third plurality of frames. The processor includes a first denoising layer and a second denoising layer. The first denoising layer includes a first denoiser, a second denoiser, and a third denoiser. The first denoiser is configured to denoise the first plurality of frames and output a first denoised frame. The second denoiser is configured to denoise the second plurality of frames and output a second denoised frame. The third denoiser is configured to denoise the third plurality of frames and output a third denoised frame. The second denoising layer includes a fourth denoiser. The fourth denoiser is configured to output a denoised frame based on the first denoised frame, the second denoised frame, and the third denoised frame.

Abstract: Systems, apparatus, and methods for super-resolution of non-uniform spatial blur. Non-uniform spatial blur presents unique challenges for conventional neural network processing. Existing implementations attempt to handle super-resolution with a “brute force” optimization. Various embodiments of the present disclosure subdivide the super-resolution function into sub-steps. “Unfolding” super-resolution into smaller closed-form functions allows for operation generic plug-and-play convolutional neural network (CNN) logic. Additionally, each step can be optimized with its own step-specific hyper parameters to improve performance.

Abstract: A method for deblurring a target image includes receiving a burst of images that includes the target image; partitioning respective images of the burst of images into respective patches; converting, to a frequency domain, the respective patches into respective transform patches; selecting a first set of corresponding transform patches from the respective transform patches, where the first set of the corresponding transform patches includes a respective transform patch for a respective image of the burst of images; obtaining, using a neural network, respective weight maps for the corresponding transform patches; obtaining a deblurred transform patch by combining the first set of corresponding transform patches using the respective weight maps; obtaining a first deblurred patch by converting the deblurred transform patch to a pixel domain; and obtaining a deblurred image of the target image using the first deblurred patch.

Abstract: Methods and systems for denoising. A method for denoising includes receiving an image from an image sensor, denoising the image, in a non-linear domain by a denoiser, by applying a noise map to the image to obtain a denoised image. Training losses for the denoiser are processed in a linear domain. The method includes storing, displaying, or transmitting an output image based on the denoised image.

Abstract: A non-blind generator or a blind generator can be used to generate a high-resolution image from a low-resolution image. The non-blind generator includes a kernel encoder, a concatenator, and a super-resolution network. The kernel encoder obtains a blur kernel to generate one or more kernel maps. The concatenator concatenates a low-resolution image to one or more kernel maps to obtain a concatenated image. The super-resolution network includes one or more convolutional layers that process the concatenated image. The super-resolution network includes a pixel shuffle layer that outputs a high-resolution image based on the processed concatenated image.

Abstract: An image capture device may detect presence of an on-housing hand within a periphery of a field of view of an optical element during capture of visual content through the optical element. The image capture device may generate an alarm to indicate the presence of the on-housing hand within the periphery of the field of view of the optical element.

Abstract: A method and apparatus for denoising a video are disclosed. The method includes obtaining multiple frames of the video. One or more frames of the video may be temporally precedent or temporally subsequent to a central frame. The method includes performing a first denoising of the multiple frames. The method includes concatenating the denoised frames into a concatenated input. The method includes performing a second denoising of the concatenated input. The method includes outputting a denoised frame based on the denoised concatenated input.

Abstract: Implementations disclosed herein include an image capture device, a system, and a method for performing multiscale denoising of an image. An image processor of the image capture device obtains a first image. The first image may be in any format and may include noise artifacts. The image processor decomposes the first image into one or more sub-images. The sub-images may range from a coarse scale to a fine scale. In some implementations, the image processor iteratively denoises each of the one or more sub-images from the coarse scale to the fine scale. The image processor reconstructs the one or more denoised sub-images to produce a denoised image. A memory of the image capture device may be configured to store the denoised image.

Abstract: Implementations disclosed herein include an image capture device, a system, and a method for performing multiscale denoising of a video. An image processor of the image capture device obtains a video frame. The video frame may be in any format and may include noise artifacts. The image processor decomposes the video frame into one or more sub-frames. In some implementations, the image processor denoises each of the one or more sub-frames. The image processor decomposes one or more video frames in a temporal buffer into one or more temporal sub-frames. The image processor denoises each of the temporal sub-frames. The image processor reconstructs the one or more denoised sub-frames and the one or more temporal sub-frames to produce a denoised video frame. A memory of the image capture device may be configured to store the denoised video frame.

Abstract: A method and apparatus for denoising a video are disclosed. The method includes obtaining multiple frames of the video. One or more frames of the video may be temporally precedent or temporally subsequent to a central frame. The method includes performing a first denoising of the multiple frames. The method includes concatenating the denoised frames into a concatenated input. The method includes performing a second denoising of the concatenated input. The method includes outputting a denoised frame based on the denoised concatenated input.

Abstract: Implementations disclosed herein include an image capture device, a system, and a method for performing multiscale denoising of a video. An image processor of the image capture device obtains a video frame. The video frame may be in any format and may include noise artifacts. The image processor decomposes the video frame into one or more sub-frames. In some implementations, the image processor denoises each of the one or more sub-frames. The image processor decomposes one or more video frames in a temporal buffer into one or more temporal sub-frames. The image processor denoises each of the temporal sub-frames. The image processor reconstructs the one or more denoised sub-frames and the one or more temporal sub-frames to produce a denoised video frame. A memory of the image capture device may be configured to store the denoised video frame.

Abstract: Implementations disclosed herein include an image capture device, a system, and a method for performing multiscale denoising of an image. An image processor of the image capture device obtains a first image. The first image may be in any format and may include noise artifacts. The image processor decomposes the first image into one or more sub-images. The sub-images may range from a coarse scale to a fine scale. In some implementations, the image processor iteratively denoises each of the one or more sub-images from the coarse scale to the fine scale. The image processor reconstructs the one or more denoised sub-images to produce a denoised image. A memory of the image capture device may be configured to store the denoised image.