公开(公告)号：US09940701B2

公开(公告)日：2018-04-10

申请号：US14865201

申请日：2015-09-25

Applicant: INTEL CORPORATION

Inventor： Michael Bronstein ,  Zachi Karni ,  Alex Bronstein ,  Ron Kimmel ,  Erez Sperling ,  Aviad Zabatani ,  Vitaly Surazhsky

IPC: G06T5/00 ,  G06K9/00 ,  G06T5/20 ,  G06T7/00 ,  H04N13/02 ,  G06K9/40

CPC classification number: G06T5/20 ,  G06K9/40 ,  G06T5/002 ,  G06T2207/10028 ,  G06T2207/20028 ,  H04N13/204

Abstract: A mechanism is described for facilitating depth image dequantization at computing devices according to one embodiment. A method of embodiments, as described herein, includes detecting a digital image of an object, the digital image including pixels having associated pixel values contaminated by noise, and side information pertaining to confidence of a value acquired in each pixel. The method may further include measuring characteristics of noise in each pixel of the digital image, and a plurality of weights relating to one or more of the pixel values, the side information, and the noise characteristics. The method may further include computing a smart filter based on a combination of the plurality of weights, applying the smart filter to filter the digital image by reducing the noise in the digital image, and outputting the filtered digital image.

公开(公告)号：US20170091917A1

公开(公告)日：2017-03-30

申请号：US14865201

申请日：2015-09-25

Applicant: INTEL CORPORATION

Inventor： Michael Bronstein ,  Zachi Karni ,  Alex Bronstein ,  Ron Kimmel ,  Erez Sperling ,  Aviad Zabatani ,  Vitaly Surazhsky

IPC: G06T5/20 ,  H04N13/02 ,  G06T7/00

CPC classification number: G06T5/20 ,  G06K9/40 ,  G06T5/002 ,  G06T2207/10028 ,  G06T2207/20028 ,  H04N13/204

Abstract: A mechanism is described for facilitating depth image dequantization at computing devices according to one embodiment. A method of embodiments, as described herein, includes detecting a digital image of an object, the digital image including pixels having associated pixel values contaminated by noise, and side information pertaining to confidence of a value acquired in each pixel. The method may further include measuring characteristics of noise in each pixel of the digital image, and a plurality of weights relating to one or more of the pixel values, the side information, and the noise characteristics. The method may further include computing a smart filter based on a combination of the plurality of weights, applying the smart filter to filter the digital image by reducing the noise in the digital image, and outputting the filtered digital image.