Depth image enhancement using perceptual texture priors

Duhyeon Bang, Hyunjung Shim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A depth camera is widely used in various applications because it provides a depth image of the scene in real time. However, due to the limited power consumption, the depth camera presents severe noises, incapable of providing the high quality 3D data. Although the smoothness prior is often employed to subside the depth noise, it discards the geometric details so to degrade the distance resolution and hinder achieving the realism in 3D contents. In this paper, we propose a perceptual-based depth image enhancement technique that automatically recovers the depth details of various textures, using a statistical framework inspired by human mechanism of perceiving surface details by texture priors. We construct the database composed of the high quality normals. Based on the recent studies in human visual perception (HVP), we select the pattern density as a primary feature to classify textures. Upon the classification results, we match and substitute the noisy input normals with high quality normals in the database. As a result, our method provides the high quality depth image preserving the surface details. We expect that our work is effective to enhance the details of depth image from 3D sensors and to provide a high-fidelity virtual reality experience

Original languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Human Vision and Electronic Imaging XX
PublisherSPIE
Volume9394
ISBN (Electronic)9781628414844
DOIs
Publication statusPublished - 2015 Jan 1
EventHuman Vision and Electronic Imaging XX - San Francisco, United States
Duration: 2015 Feb 92015 Feb 12

Other

OtherHuman Vision and Electronic Imaging XX
CountryUnited States
CitySan Francisco
Period15/2/915/2/12

Fingerprint

image enhancement
Image Enhancement
Image enhancement
Texture
textures
Textures
Cameras
Virtual reality
Electric power utilization
Camera
cameras
Sensors
Visual Perception
virtual reality
Human Perception
visual perception
Virtual Reality
Substitute
Fidelity
preserving

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Bang, D., & Shim, H. (2015). Depth image enhancement using perceptual texture priors. In Proceedings of SPIE-IS and T Electronic Imaging - Human Vision and Electronic Imaging XX (Vol. 9394). [93941C] SPIE. https://doi.org/10.1117/12.2083094
Bang, Duhyeon ; Shim, Hyunjung. / Depth image enhancement using perceptual texture priors. Proceedings of SPIE-IS and T Electronic Imaging - Human Vision and Electronic Imaging XX. Vol. 9394 SPIE, 2015.
@inproceedings{ec0337834d144bd18396487328827ec0,
title = "Depth image enhancement using perceptual texture priors",
abstract = "A depth camera is widely used in various applications because it provides a depth image of the scene in real time. However, due to the limited power consumption, the depth camera presents severe noises, incapable of providing the high quality 3D data. Although the smoothness prior is often employed to subside the depth noise, it discards the geometric details so to degrade the distance resolution and hinder achieving the realism in 3D contents. In this paper, we propose a perceptual-based depth image enhancement technique that automatically recovers the depth details of various textures, using a statistical framework inspired by human mechanism of perceiving surface details by texture priors. We construct the database composed of the high quality normals. Based on the recent studies in human visual perception (HVP), we select the pattern density as a primary feature to classify textures. Upon the classification results, we match and substitute the noisy input normals with high quality normals in the database. As a result, our method provides the high quality depth image preserving the surface details. We expect that our work is effective to enhance the details of depth image from 3D sensors and to provide a high-fidelity virtual reality experience",
author = "Duhyeon Bang and Hyunjung Shim",
year = "2015",
month = "1",
day = "1",
doi = "10.1117/12.2083094",
language = "English",
volume = "9394",
booktitle = "Proceedings of SPIE-IS and T Electronic Imaging - Human Vision and Electronic Imaging XX",
publisher = "SPIE",
address = "United States",

}

Bang, D & Shim, H 2015, Depth image enhancement using perceptual texture priors. in Proceedings of SPIE-IS and T Electronic Imaging - Human Vision and Electronic Imaging XX. vol. 9394, 93941C, SPIE, Human Vision and Electronic Imaging XX, San Francisco, United States, 15/2/9. https://doi.org/10.1117/12.2083094

Depth image enhancement using perceptual texture priors. / Bang, Duhyeon; Shim, Hyunjung.

Proceedings of SPIE-IS and T Electronic Imaging - Human Vision and Electronic Imaging XX. Vol. 9394 SPIE, 2015. 93941C.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Depth image enhancement using perceptual texture priors

AU - Bang, Duhyeon

AU - Shim, Hyunjung

PY - 2015/1/1

Y1 - 2015/1/1

N2 - A depth camera is widely used in various applications because it provides a depth image of the scene in real time. However, due to the limited power consumption, the depth camera presents severe noises, incapable of providing the high quality 3D data. Although the smoothness prior is often employed to subside the depth noise, it discards the geometric details so to degrade the distance resolution and hinder achieving the realism in 3D contents. In this paper, we propose a perceptual-based depth image enhancement technique that automatically recovers the depth details of various textures, using a statistical framework inspired by human mechanism of perceiving surface details by texture priors. We construct the database composed of the high quality normals. Based on the recent studies in human visual perception (HVP), we select the pattern density as a primary feature to classify textures. Upon the classification results, we match and substitute the noisy input normals with high quality normals in the database. As a result, our method provides the high quality depth image preserving the surface details. We expect that our work is effective to enhance the details of depth image from 3D sensors and to provide a high-fidelity virtual reality experience

AB - A depth camera is widely used in various applications because it provides a depth image of the scene in real time. However, due to the limited power consumption, the depth camera presents severe noises, incapable of providing the high quality 3D data. Although the smoothness prior is often employed to subside the depth noise, it discards the geometric details so to degrade the distance resolution and hinder achieving the realism in 3D contents. In this paper, we propose a perceptual-based depth image enhancement technique that automatically recovers the depth details of various textures, using a statistical framework inspired by human mechanism of perceiving surface details by texture priors. We construct the database composed of the high quality normals. Based on the recent studies in human visual perception (HVP), we select the pattern density as a primary feature to classify textures. Upon the classification results, we match and substitute the noisy input normals with high quality normals in the database. As a result, our method provides the high quality depth image preserving the surface details. We expect that our work is effective to enhance the details of depth image from 3D sensors and to provide a high-fidelity virtual reality experience

UR - http://www.scopus.com/inward/record.url?scp=84928475922&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928475922&partnerID=8YFLogxK

U2 - 10.1117/12.2083094

DO - 10.1117/12.2083094

M3 - Conference contribution

VL - 9394

BT - Proceedings of SPIE-IS and T Electronic Imaging - Human Vision and Electronic Imaging XX

PB - SPIE

ER -

Bang D, Shim H. Depth image enhancement using perceptual texture priors. In Proceedings of SPIE-IS and T Electronic Imaging - Human Vision and Electronic Imaging XX. Vol. 9394. SPIE. 2015. 93941C https://doi.org/10.1117/12.2083094