Qualcomm Incorporated

Nitesh Shroff

Ramin Rezaiifar

Piyush Sharma

Chiachi Sung

Exemplary methods, apparatuses, and systems for image processing are described. One or more reference images are selected based on image quality scores. At least a portion of each reference image is merged to create an output image. An output image with motion artifacts is compared to a target to correct the motion artifacts of the output image.

Reference image selection for motion ghost filtering

Systems, devices, and methods are described for efficiently super resolving a portion of an image. One embodiment involves capturing, using a camera module of a device, at least one image of a scene, and creating a higher resolution image of a user-selected region of interest. The super resolution of the region of interest may be performed by matching a high resolution grid with a grid that is at the resolution of a device camera, populating the high resolution grid with information from an image from the camera, and then populating the remaining points of the grid that are not yet populated.

Systems and methods to super resolve a user-selected region of interest

Techniques disclosed herein involve determining motion occurring in a scene between the capture of two successively-captured images of the scene using intensity gradients of pixels within the images. These techniques can be used alone or with other motion-detection techniques to identify where motion has occurred in the scene, which can be further used to reduce artifacts that may be generated when images are combined.

Detecting and compensating for motion between a flash and a no-flash image

Techniques are described for generating an all-in focus image with a capability to refocus. One example includes obtaining a first depth map associated with a plurality of captured images of a scene. The plurality of captured images may include images having different focal lengths. The method further includes obtaining a second depth map associated with the plurality of captured images, generating a composite image showing different portions of the scene in focus (based on the plurality of captured images and the first depth map), and generating a refocused image showing a selected portion of the scene in focus (based on the composite image and the second depth map).

Method and apparatus for generating an all-in-focus image

Apparatuses and methods for reading a set of images to merge together into a high dynamic range (HDR) output image are described. Images have a respective HDR weight and a respective ghost-free weight. Images are merged together using the weighted average of the set of input images using the ghost-free weight. A difference image is determined based on a difference between each pixel within a HDR output image and each respective pixel within a reference image used to create the HDR output image.

Growing community of inventors

San Diego, CA, United States of America

Nitesh Shroff