Samsung Electronics Co., Ltd.

Qiang Zhang

Ilia Ovsiannikov

Zhengping Ji

Yibing Michelle Wang

Lilong Shi

Hyun Surk Ryu

Kyoobin Lee

Gregory Waligorski

Two-dimensional (2D) color information and 3D-depth information are concurrently obtained from a 2D pixel array. The 2D pixel array is arranged in a first group of a plurality of rows. A second group of rows of the array are operable to generate 2D-color information and pixels of a third group of the array are operable to generate 3D-depth information. The first group of rows comprises a first number of rows, the second group of rows comprises a second number of rows that is equal to or less than the first number of rows, and the third group of rows comprises a third number of rows that is equal to or less than the second number of rows. In an alternating manner, 2D-color information is received from a row selected from the second group of rows and 3D-depth information is received from a row selected from the third group of rows.

Concurrent RGBZ sensor and system

An image signal processing (ISP) system is provided. The system includes a neural network trained by inputting a set of raw data images and a correlating set of desired quality output images; the neural network including an input for receiving input image data and providing processed output; wherein the processed output includes input image data that has been adjusted for at least one image quality attribute. A method and an imaging device are disclosed.

Method and apparatus of neural network based image signal processor

A method for configuring a neural network is provided. The method includes: selecting a neural network including a plurality of layers, each of the layers including a plurality of neurons for processing an input and providing an output; and, incorporating at least one switch configured to randomly select and disable at least a portion of the neurons in each layer. Another method in the computer program product is disclosed.

Method and apparatus of learning neural network via hierarchical ensemble learning

An apparatus and a method. The apparatus includes a dynamic vision sensor (DVS) configured to generate a stream of events, where an event includes a location and a binary value indicating a positive or a negative change in luminance; a sampling unit connected to the DVS and configured to sample the stream of events; and an image formation unit connected to the sampling unit and configured to form an image for each sample of the stream of events, wherein a manner of sampling by the sampling unit is adjusted to reduce variations between images formed by the image formation unit.

Method and apparatus for event sampling of dynamic vision sensor on image formation

An apparatus and a method. The apparatus includes an image representation unit configured to receive a sequence of frames generated from events sensed by a dynamic vision sensor (DVS) and generate a confidence map from non-noise events; and an image denoising unit connected to the image representation unit and configured to denoise an image in a spatio-temporal domain. The method includes receiving, by an image representation unit, a sequence of frames generated from events sensed by a DVS, and generating a confidence map from non-noise events; and denoising, by an image denoising unit connected to the image representation unit, images formed from the frames in a spatio-temporal domain.

Method and apparatus of image representation and processing for dynamic vision sensor

A method for training a neural network to perform assessments of image quality is provided. The method includes: inputting into the neural network at least one set of images, each set including an image and at least one degraded version of the image; performing comparative ranking of each image in the at least one set of images; and training the neural network with the ranking information. A neural network and image signal processing tuning system are disclosed.

Label-free non-reference image quality assessment via deep neural network

A method for enhancing at least one image within a series of images is provided. The method includes: selecting the series of images; upscaling each image within the series of images; selecting a reference image among the series of images; performing image registration to align series of images with the reference image; evaluating the series of aligned images for a subset of pixel locations that exhibit high cross-frame variation; performing learning processing to substantially reduce noise and exclude motion biases at the subset of pixel locations; performing pixel fusion from the series of aligned and processed images to produce the super-resolution reference image. A computer program product and an imaging system are disclosed.

Growing community of inventors

Pasadena, CA, United States of America

Qiang Zhang