0

SurfaceNet: Adversarial SVBRDF Estimation from a Single Image

SurfaceNet, a patch-based generative adversarial network, estimates SVBRDF material properties from single images with high-quality outputs, outperforming existing reconstruction methods.

Year
2021
Venue
ICCV 2021 10
Authors
3
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2107.11298ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

In this paper we present SurfaceNet, an approach for estimating spatially-varying bidirectional reflectance distribution function (SVBRDF) material properties from a single image. We pose the problem as an image translation task and propose a novel patch-based generative adversarial network (GAN) that is able to produce high-quality, high-resolution surface reflectance maps. The employment of the GAN paradigm has a twofold objective: 1) allowing the model to recover finer details than standard translation models; 2) reducing the domain shift between synthetic and real data distributions in an unsupervised way. An extensive evaluation, carried out on a public benchmark of synthetic and real images under different illumination conditions, shows that SurfaceNet largely outperforms existing SVBRDF reconstruction methods, both quantitatively and qualitatively. Furthermore, SurfaceNet exhibits a remarkable ability in generating high-quality maps from real samples without any supervision at training time.

Authors

3