SubdSH : subdivision-based spherical harmonics field for real-time shading-based refinement under challenging unknown illumination

This paper presents a spatial-varying illumination model for shading-based depth refinement that based on a smooth Spherical Harmonics (SH) lighting field. The proposed lighting model is able to recover shading under challenging unknown lighting conditions, thus improving the quality of recovered su...

Full description

Saved in:
Bibliographic Details
Main Authors: Deng, Teng, Zheng, Jianmin, Cai, Jianfei, Cham, Tat-Jen
Other Authors: School of Computer Science and Engineering
Format: Conference or Workshop Item
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/138276
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-138276
record_format dspace
spelling sg-ntu-dr.10356-1382762020-04-30T02:49:00Z SubdSH : subdivision-based spherical harmonics field for real-time shading-based refinement under challenging unknown illumination Deng, Teng Zheng, Jianmin Cai, Jianfei Cham, Tat-Jen School of Computer Science and Engineering 2018 IEEE Visual Communications and Image Processing (VCIP) Institute for Media Innovation (IMI) Engineering::Computer science and engineering Shape-from-shading Lighting Model This paper presents a spatial-varying illumination model for shading-based depth refinement that based on a smooth Spherical Harmonics (SH) lighting field. The proposed lighting model is able to recover shading under challenging unknown lighting conditions, thus improving the quality of recovered surface detail. To avoid over-parameterization, local lighting coefficients are treated as a vector-valued function which is represented by subdivided surfaces using Catmull-Clark subdivision. We solve our lighting model utilizing a highly parallelized scheme that recovers lighting in a few milliseconds. A real-time shading-based depth recovery system is implemented with the integration of our proposed lighting model. We conduct quantitative and qualitative evaluations on both synthetic and real world datasets under challenging illumination. The experimental results show our method outperforms the state-of-the-art real-time shading-based depth refinement system. NRF (Natl Research Foundation, S’pore) MOE (Min. of Education, S’pore) 2020-04-30T02:48:59Z 2020-04-30T02:48:59Z 2018 Conference Paper Deng, T., Zheng, J., Cai, J., & Cham, T.-J. (2018). SubdSH : subdivision-based spherical harmonics field for real-time shading-based refinement under challenging unknown illumination. 2018 IEEE Visual Communications and Image Processing (VCIP). doi:10.1109/VCIP.2018.8698629 9781538644591 https://hdl.handle.net/10356/138276 10.1109/VCIP.2018.8698629 2-s2.0-85065401561 en © 2018 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Shape-from-shading
Lighting Model
spellingShingle Engineering::Computer science and engineering
Shape-from-shading
Lighting Model
Deng, Teng
Zheng, Jianmin
Cai, Jianfei
Cham, Tat-Jen
SubdSH : subdivision-based spherical harmonics field for real-time shading-based refinement under challenging unknown illumination
description This paper presents a spatial-varying illumination model for shading-based depth refinement that based on a smooth Spherical Harmonics (SH) lighting field. The proposed lighting model is able to recover shading under challenging unknown lighting conditions, thus improving the quality of recovered surface detail. To avoid over-parameterization, local lighting coefficients are treated as a vector-valued function which is represented by subdivided surfaces using Catmull-Clark subdivision. We solve our lighting model utilizing a highly parallelized scheme that recovers lighting in a few milliseconds. A real-time shading-based depth recovery system is implemented with the integration of our proposed lighting model. We conduct quantitative and qualitative evaluations on both synthetic and real world datasets under challenging illumination. The experimental results show our method outperforms the state-of-the-art real-time shading-based depth refinement system.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Deng, Teng
Zheng, Jianmin
Cai, Jianfei
Cham, Tat-Jen
format Conference or Workshop Item
author Deng, Teng
Zheng, Jianmin
Cai, Jianfei
Cham, Tat-Jen
author_sort Deng, Teng
title SubdSH : subdivision-based spherical harmonics field for real-time shading-based refinement under challenging unknown illumination
title_short SubdSH : subdivision-based spherical harmonics field for real-time shading-based refinement under challenging unknown illumination
title_full SubdSH : subdivision-based spherical harmonics field for real-time shading-based refinement under challenging unknown illumination
title_fullStr SubdSH : subdivision-based spherical harmonics field for real-time shading-based refinement under challenging unknown illumination
title_full_unstemmed SubdSH : subdivision-based spherical harmonics field for real-time shading-based refinement under challenging unknown illumination
title_sort subdsh : subdivision-based spherical harmonics field for real-time shading-based refinement under challenging unknown illumination
publishDate 2020
url https://hdl.handle.net/10356/138276
_version_ 1681059164162359296