DEPTH-GUIDED VIDEO INPAINTING FOR AUTONOMOUS DRIVING - BAIDU COM TIMES TECH BEIJING CO LTD

Title:

DEPTH-GUIDED VIDEO INPAINTING FOR AUTONOMOUS DRIVING

Document Type and Number:

WIPO Patent Application WO/2021/237471

Kind Code:

A1

Abstract:

Systems and methods of video inpainting for autonomous driving are disclosed. For example, the method stitches a multiplicity of depth frames into a 3D map, where one or more objects in the depth frames have previously been removed. The method further projects the 3D map onto a first image frame to generate a corresponding depth map, where the first image frame includes a target inpainting region. For each target pixel within the target inpainting region of the first image frame, based on the corresponding depth map, the method further maps the target pixel within the target inpainting region of the first image frame to a candidate pixel in a second image frame. The method further determines a candidate color to fill the target pixel. The method further performs Poisson image editing on the first image frame to achieve color consistency at a boundary and between inside and outside of the target inpainting region of the first image frame. For each pixel in the target inpainting region of the first image frame, the method further traces the pixel into neighboring frames and replacing an original color of the pixel with an average of colors sampled from the neighboring frames.

Inventors:

LIAO MIAO (US)
LU FEIXIANG (CN)
ZHOU DINGFU (CN)
ZHANG SIBO (US)
YANG RUIGANG (CN)

Application Number:

PCT/CN2020/092390

Publication Date:

December 02, 2021

Filing Date:

May 26, 2020

Export Citation:

Click for automatic bibliography generation Help

Assignee:

BAIDU COM TIMES TECH BEIJING CO LTD (CN)
BAIDU USA LLC (US)

International Classes:

G06T7/50; H04N13/00

Foreign References:

CN103561258A	2014-02-05
CN110322542A	2019-10-11
CN104780355A	2015-07-15
US20160110613A1	2016-04-21
US20170061701A1	2017-03-02

Other References: