SurfaceNet: Adversarial SVBRDF Estimation from a Single Image
TL
TL;DR
SurfaceNet is presented, an approach for estimating spatially-varying bidirectional reflectance distribution function (SVBRDF) material properties from a single image that largely outperforms existing SVBRDF reconstruction methods, both quantitatively and qualitatively.
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.Source code available at https://github.com/perceivelab/surfacenet.
References27 items
1
MaterialGAN
2
Guided Fine‐Tuning for Large‐Scale Material Transfer
3
Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View Images
4
Deep inverse rendering for high-resolution SVBRDF estimation from an arbitrary number of images
5