Research map / 3D vision / Face and shape
De-Rendering the World's Revolutionary Artefacts
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 RADAR's unsupervised decomposition instead of SIRFS or Single-Image SVBRDF | Synthetic vase images · Synthetic vases | Albedo scale-invariant MSE (×10⁻²): 2.74 ± 3.28 -> 0.71 ± 0.92 | Helped |
| Use RADAR's unsupervised decomposition instead of Single-Image SVBRDF | Synthetic vase images · Synthetic vases | Normal angular deviation (degrees): 36.39 ± 6.92 -> 5.81 ± 0.51 | Helped |
| Add single-color albedo rendering loss L_alb (ablation) | RADAR · Synthetic vases | Albedo scale-invariant MSE (×10⁻²): 2.83 ± 2.28 -> 0.71 ± 0.92 | Helped |
| Add single-color albedo rendering loss L_alb (ablation) | RADAR · Synthetic vases | Pose RMSE: 2.77 ± 4.64 -> 0.43 ± 0.40 | Helped |
| Add self-supervised albedo discriminator loss L_SAD (ablation) | RADAR · Synthetic vases | Albedo scale-invariant MSE (×10⁻²): 0.75 ± 1.09 -> 0.71 ± 0.92 | Helped |
| Add self-supervised albedo discriminator loss L_SAD (ablation) | RADAR · Synthetic vases | Environment map scale-invariant MSE: 0.41 ± 0.39 -> 0.41 ± 0.37 | No clear effect |
| Add diffuse regularizer L_diff (ablation) | RADAR · Synthetic vases | Environment map scale-invariant MSE: 0.46 ± 0.35 -> 0.41 ± 0.37 | Helped |
| Add diffuse regularizer L_diff (ablation) | RADAR · Synthetic vases | Albedo scale-invariant MSE (×10⁻²): 0.82 ± 0.98 -> 0.71 ± 0.92 | Helped |
Closest papers by meaning
- Eclipse: Disambiguating Illumination and Materials using Unintended Shadows (CVPR 2024 · similarity 0.89)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025 · similarity 0.88)
- Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation (CVPR 2025 · similarity 0.86)
- Latent Intrinsics Emerge from Training to Relight (NeurIPS 2024 · similarity 0.86)
- Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields (CVPR 2024 · similarity 0.86)
- Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction (NeurIPS 2026 · 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.