Learning Photometric Stereo via Manifold-based Mapping

Yakun Ju, Muwei Jian, Junyu Dong, Kin Man Lam

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

11 Citations (Scopus)

Abstract

Three-dimensional reconstruction technologies are fundamental problems in computer vision. Photometric stereo recovers the surface normals of a 3D object from varying shading cues, prevailing in its capability for generating fine surface normal. In recent years, deep learning-based photometric stereo methods are capable of improving the surface-normal estimation under general non-Lambertian surfaces, due to its powerful fitting ability on the non-Lambertian surface. These state-of-the-art methods however usually regress the surface normal directly from the high-dimensional features, without exploring the embedded structural information. This results in the underutilization of the information available in the features. Therefore, in this paper, we propose an efficient manifold-based framework for learning-based photometric stereo, which can better map combined high-dimensional feature spaces to low-dimensional manifolds. Extensive experiments show that our method, learning with the low-dimensional manifolds, achieves more accurate surface-normal estimation, outperforming other state-of-the-art methods on the challenging DiLiGenT benchmark dataset.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages411-414
Number of pages4
ISBN (Electronic)9781728180670
DOIs
Publication statusPublished - 1 Dec 2020
Event2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020 - Virtual, Macau, China
Duration: 1 Dec 20204 Dec 2020

Publication series

Name2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020

Conference

Conference2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020
Country/TerritoryChina
CityVirtual, Macau
Period1/12/204/12/20

Keywords

  • 3D reconstruction
  • deep learning
  • manifold-based mapping
  • photometric stereo

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Media Technology

Fingerprint

Dive into the research topics of 'Learning Photometric Stereo via Manifold-based Mapping'. Together they form a unique fingerprint.

Cite this