Intel Corporation

Google Inc.

Jun Nishimura

Aleksandar Sutic

Gilad Michael

Timo Gerasimow

Chyuan-Tyng Wu

Sushma Rao

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing highlight recovery. One of the methods includes receiving raw image data of an image, the raw image data comprising, for each of a plurality of highlight regions in the image, original channel values for one or more channels of the highlight region; processing the raw image data to generate updated image data, wherein the updated image data comprises updated channel values for each highlight region in the image, and wherein, for each of one or more highlight regions of the image, one or more updated channel values of the highlight region exceed a maximum channel value according to a predetermined data precision; and performing a hue correction process on the updated channel values of the one or more highlight regions of the image to generate final channel values that satisfy the predetermined data precision.

Highlight recovery for image processing pipeline

A mechanism is described for facilitating hybrid tone mapping in camera systems according to one embodiment. A method of embodiments, as described herein, includes detecting a scene having a sequence of frames, and fusing the sequence of frames into a fused raw frame. The method may further include reconstructing the scene by performing global tone mapping and local tone mapping on the fused raw frame, and outputting an image reflecting the reconstructed scene based on the tone-mapped raw frame.

Hybrid tone mapping for consistent tone reproduction of scenes in camera systems

A mechanism is described for facilitating automatic tuning of image signal processors using reference images in image processing environments, according to one embodiment. A method of embodiments, as described herein, includes one or more processors to: receive images associated with one or more scenes captured by one or more cameras; access tuning parameters associated with functionalities within an image signal processor (ISP) pipeline; generate reference images based on the tuning parameters, wherein a reference image is associated with an image for each functionality within the ISP pipeline; and automatically tune the ISP pipeline based on selection of one or more of the reference images for one or more of the images for one or more of the functionalities.

Automatic tuning of image signal processors using reference images in image processing environments

Techniques related to temporal noise reduction of images are discussed. Such techniques may include generating a noise stream corresponding to an input image and adaptively re-combining the noise stream with a reference image corresponding to the input image and a spatially noise reduced image corresponding to the input image to generate a temporal noise reduced output image.

Motion adaptive stream processing for temporal noise reduction

An example apparatus for image processing includes a motion-adaptive image enhancer to receive motion data and an image with reduced noise. The motion-adaptive image enhancer can process an occluded region of the image based on the motion data. The motion-adaptive image enhancer can generate an enhanced image.

Processing images based on generated motion data

A method, apparatus and system for performing a demosaic operation are described. In one embodiment, the apparatus comprises: a plurality of interpolation modules to perform a plurality of interpolation operations to generate color pixel values of a first color for a plurality of pixel locations in an image region that do not have color pixel values of the first color; a first module to generate a set of color pixel values of the first color for the image region, one or more color pixel values in the set of pixel values being generated based on color pixel values of the first color from one of the plurality of interpolation modules; and a second module to select the one interpolation module based on an interpolation direction determined by color intensity gradient calculations that involve pixel values of the first color and at least one other color.

Edge sensing measure for raw image processing

A scalable rank filter and method that performs rank filtering based on input data samples are disclosed. In one embodiment, the rank filter comprises a pipeline that receives input data samples and generates an output based on the input data samples as a result of completing execution of the pipeline. The rank filter includes output logic to determine the output prior completing execution of the pipeline and outputs an indication of a median.

Scalable rank filter

A scalable rank filter and method for performing rank filtering are disclosed. In one embodiment, the rank filter comprises a W staged pipeline with W stages to receive N input data samples and operable to generate an output based on the N input data samples as a result of the W stages completing execution, where W is a bit length of the inputs and W and N are integers greater than two; and output logic coupled to the W staged pipeline to determine the output prior to all W stages completing execution and to output the median.

Growing community of inventors

San Jose, CA, United States of America

Jun Nishimura