Papers › Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising
Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising
Jon Hasselgren, Nikolai Hofmann, Jacob Munkberg
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Relighting | Stanford-ORB | NVDiffRecMC | HDR-PSNR | 24.43 | #2 of 7 | Archive leaderboard | report |
| Image Relighting | Stanford-ORB | NVDiffRecMC | LPIPS | 0.036 | #2 of 7 | Archive leaderboard | report |
| Image Relighting | Stanford-ORB | NVDiffRecMC | SSIM | 0.972 | #2 of 7 | Archive leaderboard | report |
| Inverse Rendering | Stanford-ORB | NVDiffRecMC | HDR-PSNR | 24.43 | #2 of 7 | Archive leaderboard | report |
| Surface Normals Estimation | Stanford-ORB | NVDiffRecMC | Cosine Distance | 0.04 | #1 of 7 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections