Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising
This work addresses the challenge of high-quality inverse rendering for computer vision and graphics applications, representing an incremental improvement over existing methods.
The paper tackled the problem of decomposing 3D scenes into shape, materials, and lighting from images by using a realistic shading model with Monte Carlo rendering, which improved decomposition but introduced noise; they addressed this by incorporating multiple importance sampling and denoising, enabling gradient-based optimization at low sample counts and achieving better material and light separation compared to previous work.
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.