De-rendering the World's Revolutionary Artefacts

04/08/2021
by   Shangzhe Wu, et al.
4

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.

READ FULL TEXT

page 1

page 3

page 4

page 6

page 7

page 8

page 12

page 13

research
03/30/2023

NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimation

We present a novel differentiable rendering framework for joint geometry...
research
12/26/2014

Sparkle Vision: Seeing the World through Random Specular Microfacets

In this paper, we study the problem of reproducing the world lighting fr...
research
07/05/2022

DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images

Photometric stereo, a problem of recovering 3D surface normals using ima...
research
02/12/2021

Outdoor inverse rendering from a single image using multiview self-supervision

In this paper we show how to perform scene-level inverse rendering to re...
research
04/16/2018

Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image

We propose a material acquisition approach to recover the spatially-vary...
research
06/18/2022

GAN2X: Non-Lambertian Inverse Rendering of Image GANs

2D images are observations of the 3D physical world depicted with the ge...
research
11/25/2019

Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild

We propose a method to learn 3D deformable object categories from raw si...

Please sign up or login with your details

Forgot password? Click here to reset