Research map / 3D vision / Depth and stereo
Lighting in Motion: Spatiotemporal HDR Lighting Estimation
Christophe Bolduc, Julien Philip, Li Ma, Mingming He, Paul Debevec, Jean-François Lalonde
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 direction and distance geometric condition maps (ablation) | LiMo (image) · Infinigen, diffuse sphere | RMSE: 0.229 -> 0.160 | Improved |
| add direction and distance geometric condition maps (ablation) | LiMo (image) · Infinigen, mirror sphere | angular error: 4.77 -> 4.35 | Improved |
| add diffuse spheres to HDRI optimization (ablation) | LiMo (image) · Infinigen, diffuse sphere | RMSE: 0.207 -> 0.160 | Improved |
| add diffuse spheres to HDRI optimization (ablation) | LiMo (image) · Infinigen, diffuse sphere | angular error: 3.39 -> 2.25 | Improved |
| add both diffuse spheres and geometric maps (ablation) | LiMo (image) · Infinigen, diffuse sphere | RMSE: 0.210 -> 0.160 | Improved |
| use video model instead of image model | LiMo · Dynamic video test (Combination), mirror sphere | T-LPIPS-Diff: 0.0787 -> 0.0208 | Improved |
| use video model instead of image model | LiMo · Dynamic video test (Combination), mirror sphere | RMSE: 0.29 -> 0.33 | Hurt |
| use video model instead of image model | LiMo · Infinigen, diffuse sphere | RMSE: 0.16 -> 0.22 | Hurt |
| replace 4D Lighting with LiMo (image) | LiMo · Infinigen, mirror sphere | angular error: 14.7 -> 4.4 | Improved |
| replace DiffusionLight with LiMo (image) | LiMo · Laval Indoor SV, mirror sphere | RMSE: 0.50 -> 0.30 | Improved |
| replace 4D Lighting with LiMo (video) | LiMo · Dynamic video test (Combination), mirror sphere | T-LPIPS-Diff: 0.0496 -> 0.0208 | Improved |
| replace 4D Lighting with LiMo (image) | LiMo · Dynamic video test (Combination), mirror sphere | T-LPIPS-Diff: 0.0496 -> 0.0787 | Hurt |
Closest papers by meaning
- LuxDiT: Lighting Estimation with Video Diffusion Transformer (NeurIPS 2025 · similarity 0.89)
- DiffusionLight: Light Probes for Free by Painting a Chrome Ball (CVPR 2024 · similarity 0.89)
- DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpainting (TPAMI 2026 · similarity 0.89)
- IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation (NeurIPS 2025 · similarity 0.87)
- Do Image Editing Models Understand Lighting? (NeurIPS 2026 · similarity 0.86)
- Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models (CVPR 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.
