Deep scene-scale material estimation from multi-view indoor captures

TL;DR

This paper introduces a learning-based method that automatically estimates detailed material maps from multi-view indoor scene captures, enabling realistic rendering and editing without manual input.

Contribution

It presents a CNN-based approach that leverages multi-view visual cues to produce physically-based rendering assets efficiently, improving over previous methods in speed and automation.

Findings

Assets are directly usable for rendering and editing.

Method is significantly faster than previous solutions.

Produces high-quality material maps from multi-view data.

Abstract

The movie and video game industries have adopted photogrammetry as a way to create digital 3D assets from multiple photographs of a real-world scene. But photogrammetry algorithms typically output an RGB texture atlas of the scene that only serves as visual guidance for skilled artists to create material maps suitable for physically-based rendering. We present a learning-based approach that automatically produces digital assets ready for physically-based rendering, by estimating approximate material maps from multi-view captures of indoor scenes that are used with retopologized geometry. We base our approach on a material estimation Convolutional Neural Network (CNN) that we execute on each input image. We leverage the view-dependent visual cues provided by the multiple observations of the scene by gathering, for each pixel of a given image, the color of the corresponding point in other images. This image-space CNN provides us with an ensemble of predictions, which we merge in texture space as the last step of our approach. Our results demonstrate that the recovered assets can be directly used for physically-based rendering and editing of real indoor scenes from any viewpoint and novel lighting. Our method generates approximate material maps in a fraction of time compared to the closest previous solutions.