Research map / 3D vision / Depth and stereo
InverseRenderNet: Learning Single Image Inverse Rendering
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use InverseRenderNet instead of Fan et al. | Intrinsic image decomposition on IIW · IIW | WHDR: 14.5 -> 21.4 | Hurt |
| Use InverseRenderNet instead of Li et al. | Albedo estimation · MegaDepth | MSE: 0.0171 -> 0.0170 | Helped |
| Use InverseRenderNet instead of Li et al. | Albedo estimation · MegaDepth | LMSE: 0.0637 -> 0.0718 | Hurt |
| Use InverseRenderNet instead of Li et al. | Albedo estimation · MegaDepth | DSSIM: 0.208 -> 0.201 | Helped |
| Use InverseRenderNet instead of Li et al. | Normal estimation · MegaDepth | Mean angular error: 50.6 -> 37.7 | Helped |
| Use InverseRenderNet instead of SIRFS | Normal estimation · MegaDepth | Median angular error: 48.5 -> 34.8 | Helped |
Closest papers by meaning
- Neural Inverse Rendering for General Reflectance Photometric Stereo (ICML 2018 · similarity 0.90)
- MVInverse: Feed-forward Multiview Inverse Rendering in Seconds (CVPR 2026 · similarity 0.89)
- Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces (CVPR 2021 · similarity 0.89)
- Modeling Indirect Illumination for Inverse Rendering (CVPR 2022 · similarity 0.88)
- InverseFaceNet: Deep Monocular Inverse Face Rendering (CVPR 2018 · similarity 0.88)
- Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance (CVPR 2024 · 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.