De-rendering the World's Revolutionary Artefacts

CVPR 2021

De-rendering the World's Revolutionary Artefacts

Apr 08, 2021
|
87 views
|
Details
Abstract: Recent works have shown exciting results in unsupervised image de-rendering -- learning to decompose 3D shape, appearance, and lighting from single-image collections without explicit supervision. However, many of these assume simplistic material and lighting models. We propose a method, termed RADAR, that can recover environment illumination and surface materials from real single-image collections, relying neither on explicit 3D supervision, nor on multi-view or multi-light images. Specifically, we focus on rotationally symmetric artefacts that exhibit challenging surface properties including specular reflections, such as vases. We introduce a novel self-supervised albedo discriminator, which allows the model to recover plausible albedo without requiring any ground-truth during training. In conjunction with a shape reconstruction module exploiting rotational symmetry, we present an end-to-end learning framework that is able to de-render the world's revolutionary artefacts. We conduct experiments on a real vase dataset and demonstrate compelling decomposition results, allowing for applications including free-viewpoint rendering and relighting. Authors: Shangzhe Wu, Ameesh Makadia, Jiajun Wu, Noah Snavely, Richard Tucker, Angjoo Kanazawa (University of Oxford, Stanford University, University of California, Berkeley, Google Research)

Comments
loading...