Deep polarization imaging for 3D shape and SVBRDF acquisition

File Description SizeFormat 
04741-finalversion.pdfFile embargoed until 01 January 100003.31 MBAdobe PDF    Request a copy
Title: Deep polarization imaging for 3D shape and SVBRDF acquisition
Authors: Deschaintre, V
Lin, Y
Ghosh, A
Item Type: Conference Paper
Abstract: We present a novel method for efficient acquisition of shape and spatially varying reflectance of 3D objects using polarization cues. Unlike previous works that have exploited polarization to estimate material or object appearance under certain constraints (known shape or multiview acquisition), we lift such restrictions by coupling polarization imaging with deep learning to achieve high quality estimate of 3D object shape (surface normals and depth)and SVBRDF using single-view polarization imaging under frontal flash illumination. In addition to acquired polarization images, we provide our deep network with strong novel cues related to shape and reflectance, in the form of a normalized Stokes map and an estimate of diffuse color. We additionally describe modifications to network architecture and training loss which provide further qualitative improvements. We demonstrate our approach to achieve superior results compared to recent works employing deep learning in conjunction with flash illumination.
Date of Acceptance: 29-Mar-2021
URI: http://hdl.handle.net/10044/1/89191
Publisher: IEEE
Copyright Statement: This paper is embargoed until publication.
Sponsor/Funder: Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: EP/N006259/1
Conference Name: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publication Status: Accepted
Start Date: 2021-06-19
Finish Date: 2021-06-25
Conference Place: Virtual
Embargo Date: publication subject to indefinite embargo
Appears in Collections:Computing