2019 International Conference on 3D Immersion (IC3D) 2019
DOI: 10.1109/ic3d48390.2019.8975995
|View full text |Cite
|
Sign up to set email alerts
|

MPEG-I Depth Estimation Reference Software

Abstract: For enabling virtual reality on natural content, Depth Image-Based Rendering (DIBR) techniques have been steadily developed over the past decade, but their quality highly depends on that of the depth estimation. This paper is an attempt to deliver good-quality Depth Estimation Reference Software (DERS) that is well-structured for further use in the worldwide MPEG standardization committee. The existing DERS has been refactored, debugged and extended to any number of input views for generating accurate depth ma… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
25
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
4
4

Relationship

3
5

Authors

Journals

citations
Cited by 26 publications
(26 citation statements)
references
References 10 publications
0
25
0
Order By: Relevance
“…The Immersive sub-community of the Moving Picture Experts Group (MPEG-I, developing standards for immersive video compression) divides DIBR in two steps after the cameras calibration: 1) depth estimation and 2) rendering. MPEG-I provides two reference software for those steps [12,27]. For natural scenes, the depth map can be acquired with a depth sensing device [40] or by computing the disparity between the input viewpoints [27].…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…The Immersive sub-community of the Moving Picture Experts Group (MPEG-I, developing standards for immersive video compression) divides DIBR in two steps after the cameras calibration: 1) depth estimation and 2) rendering. MPEG-I provides two reference software for those steps [12,27]. For natural scenes, the depth map can be acquired with a depth sensing device [40] or by computing the disparity between the input viewpoints [27].…”
Section: Related Workmentioning
confidence: 99%
“…MPEG-I provides two reference software for those steps [12,27]. For natural scenes, the depth map can be acquired with a depth sensing device [40] or by computing the disparity between the input viewpoints [27]. Once the depth map is estimated for each input image, the color pixels of each view are displaced,using this depth map, to the location of the target view [30,12].…”
Section: Related Workmentioning
confidence: 99%
“…Considered the algorithm with the best quality depth map generation, graph cuts were implemented in DERS to fulfill the quality requirements of immersive video applications. The quality and processing time needed by this software were studied in another work [31], showing that for generating these highly detailed depth maps, the processing time needed oscillates between hundred and thousand of seconds. Therefore, although DERS can be considered a higher bound in depth map quality, its high processing time forces its use offline.…”
Section: Related Workmentioning
confidence: 99%
“…MPEG DERS [31] has been the reference software for depth estimation in MPEG-I for several years. Its use is mainly focused on the generation of high-quality depth maps for immersive video applications using YUV images as input without considering the processing time needed.…”
Section: Background: Mpeg Depth Estimation Reference Software (Ders)mentioning
confidence: 99%
“…We have used the MPEG-I Visual Depth Estimation Reference Software (DERS) based on graph cut [10,11], which has been improved to yield view-consistent depth maps with temporal consistency (for video) [12], cf. the visual example in [13].…”
Section: Depth Estimationmentioning
confidence: 99%