Research map / 3D vision / Depth and stereo
Materialist: Physically Based Editing Using Single-Image Inverse Rendering
Lezhong Wang, Duc Minh Tran, Ruiqi Cui, Thomson TG, Anders Bjorholm Dahl, Siavash Arjomand Bigdeli, Jeppe Revall Frisvad, Manmohan Chandraker
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add MatNet predicted materials during envmap optimization (ablation) | Envmap optimization · Envmap optimization (constructed dataset) | SH error: 4.554 -> 0.474 | Improved |
| add MatNet predicted materials during envmap optimization (ablation) | Envmap optimization · Envmap optimization (constructed dataset) | Render PSNR: 17.300 -> 20.048 | Improved |
| use spherical unit-vector encoding instead of UV coordinates (ablation) | Envmap MLP · Envmap 512x256 | SH error: 0.503 vs 0.472 | Improved |
| use spherical unit-vector encoding instead of UV coordinates (ablation) | Envmap MLP · Envmap 512x256 | Render PSNR: 19.87 -> 20.05 | Improved |
| raise envmap resolution from 32x16 to 512x256 (ablation) | Envmap optimization · Envmap, reflective surfaces | PSNR: 25.042 -> 26.540 | Improved |
| raise envmap resolution from 32x16 to 512x256 (ablation) | Envmap optimization · Envmap 512x256 | Envmap MSE: 0.144 -> 0.866 | Hurt |
| use GT instead of inpainted background (ablation) | Transparency editing · Symmetric objects | PSNR: 20.162 -> 20.308 | No clear effect |
| use GT instead of inpainted background (ablation) | Transparency editing · Asymmetric objects | PSNR: 19.278 -> 18.667 | Hurt |
| change assumed FOV from 35 to 42 degrees (ablation) | Mesh reconstruction · FOV sensitivity (synthetic) | PSNR: 28.56 -> 27.85 | No clear effect |
| add 50% noise to predicted thickness (ablation) | Transparency editing · Thickness robustness | PSNR: 22.23 -> 21.94 | No clear effect |
| add super-resolution post-processing (ablation) | Direct optimization output · Material editing user study | preference sum: 7.36 -> 8.96 | Improved |
| compare against Alchemist on material editing | Materialist direct output · Material editing user study | preference sum: 7.68 vs 7.36 | Mixed |
Closest papers by meaning
- Material Editing Using a Physically Based Rendering Network (ICCV 2017 · similarity 0.91)
- PhySG: Inverse Rendering With Spherical Gaussians for Physics-Based Material Editing and Relighting (CVPR 2021 · similarity 0.89)
- OMG: Opacity Matters in Material Modeling with Gaussian Splatting (ICLR 2025 · similarity 0.87)
- Material Palette: Extraction of Materials from a Single Image (CVPR 2024 · similarity 0.86)
- PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields (CVPR 2025 · similarity 0.86)
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
