Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising

TL;DR

This paper introduces a novel inverse rendering pipeline that combines Monte Carlo ray tracing, importance sampling, and denoising to improve the decomposition of shape, material, and lighting from images.

Contribution

It presents an efficient joint reconstruction method using realistic shading models with noise reduction techniques, advancing inverse rendering accuracy and convergence.

Findings

Enhanced shape, material, and lighting separation compared to previous methods.

Effective denoising integrated into the inverse rendering process.

Improved convergence at low sample counts.

Abstract

Recent advances in differentiable rendering have enabled high-quality reconstruction of 3D scenes from multi-view images. Most methods rely on simple rendering algorithms: pre-filtered direct lighting or learned representations of irradiance. We show that a more realistic shading model, incorporating ray tracing and Monte Carlo integration, substantially improves decomposition into shape, materials & lighting. Unfortunately, Monte Carlo integration provides estimates with significant noise, even at large sample counts, which makes gradient-based inverse rendering very challenging. To address this, we incorporate multiple importance sampling and denoising in a novel inverse rendering pipeline. This substantially improves convergence and enables gradient-based optimization at low sample counts. We present an efficient method to jointly reconstruct geometry (explicit triangle meshes), materials, and lighting, which substantially improves material and light separation compared to previous work. We argue that denoising can become an integral part of high quality inverse rendering pipelines.