Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 25.01.2022 at 9:00 AM CET
Settings

Settings

Goto Application

1. US20210366139 - METHOD AND APPARATUS FOR GENERATING DEPTH IMAGE

Office
United States of America
Application Number 17225574
Application Date 08.04.2021
Publication Number 20210366139
Publication Date 25.11.2021
Publication Kind A1
IPC
G06T 7/55
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
50Depth or shape recovery
55from multiple images
CPC
G06T 2207/20076
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
20Special algorithmic details
20076Probabilistic image processing
G06T 7/55
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
50Depth or shape recovery
55from multiple images
G06T 2207/10048
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
10Image acquisition modality
10048Infrared image
G06T 2207/10024
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
10Image acquisition modality
10024Color image
G06T 2207/10028
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
10Image acquisition modality
10028Range image; Depth image; 3D point clouds
Applicants SAMSUNG ELECTRONICS CO., LTD.
Inventors Jihye KIM
Seon Min RHEE
Heewon KIM
Seungju HAN
Jaejoon HAN
Title
(EN) METHOD AND APPARATUS FOR GENERATING DEPTH IMAGE
Abstract
(EN)

A method and apparatus for generating a depth image are provided. The apparatus receives an input image, extracts a feature corresponding to the input image, generates features for each depth resolution by decoding the feature using decoders corresponding to different depth resolutions, estimates probability distributions for each depth resolution by progressively refining the features for each depth resolution, and generates a target depth image corresponding to the input image based on a final estimated probability distribution from among the probability distributions for each depth resolution.