Research map / 3D vision / Depth and stereo
Inferring Light Fields From Shadows
Read the paperCheck 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 |
|---|---|---|---|
| Replace a pinspeck occluder with a sphere occluder (ablation) | Light-field reconstruction method · Simulated two-square scene | PSNR: 11.37dB -> 14.09dB | Helped |
| Replace a sphere occluder with two pinspecks at different depths (ablation) | Light-field reconstruction method · Simulated two-square scene | PSNR: 14.09dB -> 18.16dB | Helped |
| Replace two pinspecks at different depths with multiple spheres (ablation) | Light-field reconstruction method · Simulated two-square scene | PSNR: 18.16dB -> 20.78dB | Helped |
| Replace multiple spheres with multiple plants (ablation) | Light-field reconstruction method · Simulated two-square scene | PSNR: 20.78dB -> 21.21dB | Helped |
Closest papers by meaning
- Using Unknown Occluders to Recover Hidden Scenes (CVPR 2019 · similarity 0.88)
- Eclipse: Disambiguating Illumination and Materials using Unintended Shadows (CVPR 2024 · similarity 0.87)
- Joint Shadow Generation and Relighting via Light-Geometry Interaction Maps (ICLR 2026 · similarity 0.86)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025 · similarity 0.84)
- OmniSR: Shadow Removal Under Direct and Indirect Lighting (AAAI 2025 · similarity 0.84)
- MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting (NeurIPS 2025 · similarity 0.84)
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.