Research map / 3D vision / Face and shape
Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization With Spatially-Varying Lighting
Robert Maier, Kihwan Kim, Daniel Cremers, Jan Kautz, Matthias Niessner
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 |
|---|---|---|---|
| replace global SH lighting with spatially-varying SH (subvolume 0.05) (ablation) | Intrinsic3D shading model · Fountain | shading MAD: 22.973 -> 10.263 | Improved |
| replace global SH lighting with spatially-varying SH (subvolume 0.05) (ablation) | Intrinsic3D shading model · Lucy | shading MAD: 22.190 -> 11.863 | Improved |
| replace global SH lighting with spatially-varying SH (subvolume 0.05) (ablation) | Intrinsic3D shading model · Relief | shading MAD: 13.818 -> 8.339 | Improved |
| replace global SH lighting with spatially-varying SH (subvolume 0.05) (ablation) | Intrinsic3D shading model · Lion | shading MAD: 30.895 -> 13.468 | Improved |
| replace global SH lighting with spatially-varying SH (subvolume 0.05) (ablation) | Intrinsic3D shading model · Tomb Statuary | shading MAD: 33.716 -> 26.433 | Improved |
| replace global SH lighting with spatially-varying SH (subvolume 0.05) (ablation) | Intrinsic3D shading model · Bricks | shading MAD: 29.327 -> 19.476 | Improved |
| replace global SH lighting with spatially-varying SH (subvolume 0.05) (ablation) | Intrinsic3D shading model · Hieroglyphics | shading MAD: 15.710 -> 9.998 | Improved |
| replace global SH lighting with spatially-varying SH (subvolume 0.05) (ablation) | Intrinsic3D shading model · Gate | shading MAD: 46.463 -> 12.947 | Improved |
| use Intrinsic3D joint optimization instead of Zollhofer et al. [30] | geometry refinement · Frog (synthetic) | MAD to ground truth (mm): 0.278mm -> 0.222mm (20.14% improvement) | Improved |
| decrease SVSH subvolume size from 0.1 to 0.05 (ablation) | Intrinsic3D shading model · Hieroglyphics | shading MAD: 12.448 -> 9.998 (but 0.2 -> 0.1: 15.206 -> 11.140 then 0.1 -> 0.05 step 11.140 -> 12.448 earlier) | Mixed |
Closest papers by meaning
- Joint Texture and Geometry Optimization for RGB-D Reconstruction (CVPR 2020 · similarity 0.89)
- Towards Scalable Multi-View Reconstruction of Geometry and Materials (TPAMI 2023 · similarity 0.89)
- ARM: Appearance Reconstruction Model for Relightable 3D Generation (CVPR 2025 · similarity 0.86)
- SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement (CVPR 2025 · similarity 0.86)
- IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations (ICLR 2025 · similarity 0.85)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025 · similarity 0.85)
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.
