Skip to content

Augmenting depth estimation from deep convolutional neural network using multi-spectral photometric stereo

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

Multi-Spectral Photometric Stereo can recover surface normals from a single image, but requires an initial estimate of the normals due to the tangle of the illumination, reflectance and camera responses on each of the RGB channels. Instead of employing a depth sensor or binocular stereo device, in this paper, we propose a method to estimate fine-scale geometry structures with the popular Deep Convolutional Neural Networks (CNNs). We train the network with rendered images of synthetic 3D objects, and apply the trained model with real world data. The CNN is used to estimate a rough prediction of the depth, then the normals from Multi-Spectral Photometric Stereo are progressively refined accordingly. Experiments demonstrate the competitive results of our method for improving the depth estimation.
Original languageEnglish
Title of host publication2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI)
ISBN (Electronic)978-1-5386-0435-9, 978-1-5386-0434-2
ISBN (Print)978-1-5386-1591-1
Publication statusPublished - 28 Jun 2018
Event14th IEEE International Conference on Ubiquitous Intelligence and Computing - San Francisco, United States
Duration: 4 Aug 20178 Aug 2017


Conference14th IEEE International Conference on Ubiquitous Intelligence and Computing
Abbreviated titleUIC 2017
CountryUnited States
CitySan Francisco
Internet address


  • Augmenting Depth Estimation from Deep Convolutional Neural Network_UIC2017

    Rights statement: © © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

    Accepted author manuscript (Post-print), 1.24 MB, PDF document

Related information

Relations Get citation (various referencing formats)

ID: 7993775