Precise depth map upsampling and enhancement based on edge-preserving fusion filters

Ting An Chang, Jar-Ferr Yang

Research output: Contribution to journalArticle

Abstract

A texture image plus its associated depth map is the simplest representation of a three-dimensional image and video signals and can be further encoded for effective transmission. Since it contains fewer variations, a depth map can be coded with much lower resolution than a texture image. Furthermore, the resolution of depth capture devices is usually also lower. Thus, a low-resolution depth map with possible noise requires appropriate interpolation to restore it to full resolution and remove noise. In this study, the authors propose potency guided upsampling and adaptive gradient fusion filters to enhance the erroneous depth maps. The proposed depth map enhancement system can successfully suppress noise, fill missing values, sharpen foreground objects, and smooth background regions simultaneously. Their experimental results show that the proposed methods perform better in terms of both visual and subjective metrics than the classic methods and achieve results that are visually comparable with those of some time-consuming methods.

Original languageEnglish
Pages (from-to)651-658
Number of pages8
JournalIET Computer Vision
Volume12
Issue number5
DOIs
Publication statusPublished - 2018 Aug 1

Fingerprint

Fusion reactions
Textures
Interpolation

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

@article{926ea8cf1b11412582a72f0021d0196a,
title = "Precise depth map upsampling and enhancement based on edge-preserving fusion filters",
abstract = "A texture image plus its associated depth map is the simplest representation of a three-dimensional image and video signals and can be further encoded for effective transmission. Since it contains fewer variations, a depth map can be coded with much lower resolution than a texture image. Furthermore, the resolution of depth capture devices is usually also lower. Thus, a low-resolution depth map with possible noise requires appropriate interpolation to restore it to full resolution and remove noise. In this study, the authors propose potency guided upsampling and adaptive gradient fusion filters to enhance the erroneous depth maps. The proposed depth map enhancement system can successfully suppress noise, fill missing values, sharpen foreground objects, and smooth background regions simultaneously. Their experimental results show that the proposed methods perform better in terms of both visual and subjective metrics than the classic methods and achieve results that are visually comparable with those of some time-consuming methods.",
author = "Chang, {Ting An} and Jar-Ferr Yang",
year = "2018",
month = "8",
day = "1",
doi = "10.1049/iet-cvi.2017.0336",
language = "English",
volume = "12",
pages = "651--658",
journal = "IET Computer Vision",
issn = "1751-9632",
publisher = "Institution of Engineering and Technology",
number = "5",

}

Precise depth map upsampling and enhancement based on edge-preserving fusion filters. / Chang, Ting An; Yang, Jar-Ferr.

In: IET Computer Vision, Vol. 12, No. 5, 01.08.2018, p. 651-658.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Precise depth map upsampling and enhancement based on edge-preserving fusion filters

AU - Chang, Ting An

AU - Yang, Jar-Ferr

PY - 2018/8/1

Y1 - 2018/8/1

N2 - A texture image plus its associated depth map is the simplest representation of a three-dimensional image and video signals and can be further encoded for effective transmission. Since it contains fewer variations, a depth map can be coded with much lower resolution than a texture image. Furthermore, the resolution of depth capture devices is usually also lower. Thus, a low-resolution depth map with possible noise requires appropriate interpolation to restore it to full resolution and remove noise. In this study, the authors propose potency guided upsampling and adaptive gradient fusion filters to enhance the erroneous depth maps. The proposed depth map enhancement system can successfully suppress noise, fill missing values, sharpen foreground objects, and smooth background regions simultaneously. Their experimental results show that the proposed methods perform better in terms of both visual and subjective metrics than the classic methods and achieve results that are visually comparable with those of some time-consuming methods.

AB - A texture image plus its associated depth map is the simplest representation of a three-dimensional image and video signals and can be further encoded for effective transmission. Since it contains fewer variations, a depth map can be coded with much lower resolution than a texture image. Furthermore, the resolution of depth capture devices is usually also lower. Thus, a low-resolution depth map with possible noise requires appropriate interpolation to restore it to full resolution and remove noise. In this study, the authors propose potency guided upsampling and adaptive gradient fusion filters to enhance the erroneous depth maps. The proposed depth map enhancement system can successfully suppress noise, fill missing values, sharpen foreground objects, and smooth background regions simultaneously. Their experimental results show that the proposed methods perform better in terms of both visual and subjective metrics than the classic methods and achieve results that are visually comparable with those of some time-consuming methods.

UR - http://www.scopus.com/inward/record.url?scp=85050249455&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050249455&partnerID=8YFLogxK

U2 - 10.1049/iet-cvi.2017.0336

DO - 10.1049/iet-cvi.2017.0336

M3 - Article

VL - 12

SP - 651

EP - 658

JO - IET Computer Vision

JF - IET Computer Vision

SN - 1751-9632

IS - 5

ER -