Research map / Learning theory and algorithms / Optimal transport
Sparse Needlets for Lighting Estimation With Spherical Transport Loss
Fangneng Zhan, Changgong Zhang, Wenbo Hu, Shijian Lu, Feiying Ma, Xuansong Xie, Ling Shao
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 |
|---|---|---|---|
| use needlets instead of spherical harmonics, both with L2 (ablation) | NeedleLight · Laval Indoor HDR (rendered 300 images) | STD: 7.14 -> 4.93 | Improved |
| add soft thresholding (sparse needlets) with L2 loss (ablation) | NeedleLight · Laval Indoor HDR (rendered 300 images) | STD: 4.93 -> 4.74 | Improved |
| add spherical transport loss to sparse needlets with L2 (ablation) | NeedleLight · Laval Indoor HDR (rendered 300 images) | STD: 4.74 -> 4.21 | Improved |
| add L2 loss to sparse needlets with STL (ablation) | NeedleLight · Laval Indoor HDR (rendered 300 images) | STD: 4.51 -> 4.21 | Improved |
| add STL to spherical harmonic coefficients (ablation) | SH basis · Laval Indoor HDR (rendered 300 images) | STD: 7.14 -> 7.13 | No clear effect |
| add STL to spherical Gaussian coefficients (ablation) | SG basis · Laval Indoor HDR (rendered 300 images) | STD: 6.01 -> 5.74 | Improved |
| add STL to spherical distribution coefficients (ablation) | SD basis · Laval Indoor HDR (rendered 300 images) | STD: 5.75 -> 5.54 | Improved |
| add STL to Haar coefficients (ablation) | Haar basis · Laval Indoor HDR (rendered 300 images) | STD: 6.07 -> 5.83 | Improved |
| add STL to SN(jmax=3) with L2 (ablation) | needlets · Laval Indoor HDR (rendered 300 images) | STD: 5.32 -> 4.93 | Improved |
| use soft instead of hard thresholding (ablation) | SN(jmax=3) · Laval Indoor HDR (rendered 300 images) | STD: 4.51 -> 4.21 | Improved |
| raise needlet order from jmax=1 to jmax=3 (ablation) | SN with L2+STL · Laval Indoor HDR (rendered 300 images) | STD: 7.18 -> 4.93 | Improved |
| raise needlet order from jmax=3 to jmax=4 (ablation) | SN with L2+STL · Laval Indoor HDR (rendered 300 images) | STD: 4.93 -> 4.96 | No clear effect |
Closest papers by meaning
- EMLight: Lighting Estimation via Spherical Distribution Approximation (AAAI 2021 · similarity 0.88)
- Estimating Spatially-Varying Lighting in Urban Scenes with Disentangled Representation (ECCV 2022 · similarity 0.86)
- Neural Illumination: Lighting Prediction for Indoor Environments (CVPR 2019 · similarity 0.86)
- LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation (CVPR 2024 · similarity 0.86)
- MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting (NeurIPS 2025 · similarity 0.84)
- Do Image Editing Models Understand Lighting? (NeurIPS 2026 · 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.
