"Deep Inverse Rendering for High Resolution SVBRDF Estimation from an Arbitrary Number of Images"
Duan Gao, Xiao Li, Yue Dong, Pieter Peers, Kun Xu, and Xin Tong

ACM Transactions on Graphics, Volume 37, Issue 4, July 2019
Abstract
In this paper we present a unified deep inverse rendering framework for estimating the spatially-varying appearance properties of a planar exemplar from an arbitrary number of input photographs, ranging from just a single photograph to many photographs. The precision of the estimated appearance scales from plausible when the input photographs fails to capture all the reflectance information, to accurate for large input sets. A key distinguishing feature of our framework is that it directly optimizes for the appearance parameters in a latent embedded space of spatially-varying appearance, such that no handcrafted heuristics are needed to regularize the optimization. This latent embedding is learned through a fully convolutional auto-encoder that has been designed to regularize the optimization. Our framework not only supports an arbitrary number of input photographs, but also at high resolution. We demonstrate and evaluate our deep inverse rendering solution on a wide variety of publicly available datasets.


Download
Supplementary Material
Bibtex
@article{Gao:2019:DIR,
author = {Gao, Duan and Li, Xiao and Dong, Yue and Peers, Pieter and Xu, Kun and Tong, Xin},
title = {Deep Inverse Rendering for High Resolution {SVBRDF} Estimation from an Arbitrary Number of Images},
month = {July},
year = {2019},
journal = {ACM Transactions on Graphics},
volume = {37},
number = {4},
doi = {https://doi.org/10.1145/3306346.3323042},
}
Stats: