Techniques for using motion data to generate a high resolution output color image from multiple images having sparse color information are disclosed. A camera generates multiple images. The camera's sensor is configured to have a sparse Bayer pattern. While the camera is generating the images, IMU data for each image is acquired. The IMU data indicates a corresponding pose the camera was in while the camera generated each image. The images and the IMU data are fed as input into a motion model. The motion model performs temporal filtering on the images and uses the IMU data to generate a red-only image, a green-only image, and a blue-only image. A high resolution output color image is generated by combining the red-only image, the green-only image, and the blue-only image.

An image processing method includes a first step of acquiring input data including a captured image and optical system information relating to a state of an optical system used for capturing the captured image and a second step of inputting the input data to a machine learning model and of generating an estimated image acquired by sharpening the captured image or by reshaping blurs included in the captured image.

An improved method and apparatus for enhancing an inspection image in a charged-particle beam inspection system. An improved method for enhancing an inspection image comprises acquiring a first image and a second image of multiple stacked layers of a sample that are taken with a first focal point and a second focal point, respectively, associating a first segment of the first image with a first layer among the multiple stacked layers and associating a second segment of the second image with a second layer among the multiple stacked layers, updating the first segment based on a first reference image corresponding to the first layer and updating the second segment based on a second reference image corresponding to the second layer, and combining the updated first segment and the updated second segment to generate a combined image including the first layer and the second layer.

An apparatus includes an acquisition unit configured to acquire distance information that indicates a distance to a subject on each predetermined region in a captured image, a control unit configured to adjust a focus position, and a storage unit configured to store first distance information acquired by the acquisition unit in response to the adjusted focus position. The control unit readjusts the focus position based on the first distance information and second distance information acquired by the acquisition unit.

A processor-implemented method with liveness detection includes: receiving a plurality of phase images of different phases; generating a plurality of preprocessed phase images by performing preprocessing, including edge enhancement processing, on the plurality of phase images of different phases; generating a plurality of differential images based on the preprocessed phase images; generating a plurality of low-resolution differential images having lower resolutions than the differential images, based on the differential images; generating a minimum map image based on the low-resolution differential images; and performing a liveness detection on an object in the phase images based on the minimum map image.

A computer-implemented method executed by at least one processor for applying rolling shutter (RS)-aware spatially varying differential homography fields for simultaneous RS distortion removal and image stitching is presented. The method includes inputting two consecutive frames including RS distortions from a video stream, performing keypoint detection and matching to extract correspondences between the two consecutive frames, feeding the correspondences between the two consecutive frames into an RS-aware differential homography estimation component to filter out outlier correspondences, sending inlier correspondences to an RS-aware spatially varying differential homography field estimation component to compute an RS-aware spatially varying differential homography field, and using the RS-aware spatially varying differential homography field in an RS stitching and correction component to produce stitched images with removal of the RS distortions.

An image enhancement system and method based on a generative adversarial network (GAN) model. The image enhancement system includes an acquiring unit, a training unit and an enhancement unit. The acquiring unit is configured to acquire a first image of a driving environment captured by a camera of a first vehicle and a second image of the driving environment captured by a camera of a second vehicle. The training unit is configured to train a GAN by using the first training image to obtain an image enhancement model. The enhancement unit is configured to enhance the second image by inputting the second image into the image enhancement model.

A high depth of field image generating apparatus according to the present disclosure includes a region segmentation unit which segments a region for a stereo image to generate region data, a depth estimating unit which estimates depths for the stereo image to generate depth data, and a high depth of field image generating unit which generates a high depth of field image from the stereo image, the region data, and the depth data.

To replace text in a digital video image sequence, a system will process frames of the sequence to: define a region of interest (ROI) with original text in each of the frames; use the ROIs to select a reference frame from the sequence; select a target frame from the sequence; determine a transform function between the ROI of the reference frame and the ROI of the target frame; replace the original text in the ROI of the reference frame with replacement text to yield a modified reference frame ROI; and use the transform function to transform the modified reference frame ROI to a modified target frame ROI in which the original text is replaced with the replacement text. The system will then insert the modified target frame ROI into the target frame to produce a modified target frame. This process may repeat for other target frames of the sequence.

A digital image sequence with multiple image frames can be enhanced. An appearance graph can be determined from the digital image sequence. The appearance graph includes prime layer nodes. Each prime layer node can represent a distinctive visual style. A prime layer image sequence can be computed for each prime layer node that matches the visual style represented by the prime layer node. An enhanced image sequence can be generated by blending at least two prime layer image sequences as defined by the appearance graph.