Research map / 3D vision / Depth and stereo
L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing
Ziyu Chen, Chenjing Ding, Jianfei Guo, Dongliang Wang, Yikang Li, Xuan Xiao, Wei Wu, Li Song
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 L-Tracing instead of volumetric integration | light visibility estimation · 1024 points x 512 lights | time (s): 13.36 -> 1.07 | Improved |
| use L-Tracing instead of volumetric integration | light visibility estimation · 4096 points x 512 lights | time (s): 64.75 -> 4.13 | Improved |
| use L-Tracing (binary visibility) instead of volume integration (ablation) | reflectance factorization · NeRFactor synthetic, albedo | PSNR: 27.594 -> 27.296 | Hurt |
| use L-Tracing (binary visibility) instead of volume integration (ablation) | reflectance factorization · NeRFactor synthetic, view interpolation | PSNR: 32.229 -> 31.194 | Hurt |
| use L-Tracing (binary visibility) instead of volume integration (ablation) | reflectance factorization · NeRFactor synthetic, HDR relighting | SSIM: 0.917 -> 0.920 | Improved |
| use L-Tracing instead of volume integration (ablation) | light visibility quality · drums OLAT2 | shadow sharpness (qualitative) | Improved |
| increase tracing iterations from 20 to 80 (ablation) | L-Tracing framework · NeRFactor synthetic, view interpolation | PSNR: 31.194 -> 31.889 | No clear effect |
| increase tracing iterations from 20 to 80 (ablation) | L-Tracing framework · NeRFactor synthetic, view interpolation | LPIPS: 0.063 -> 0.060 | No clear effect |
| use L-Tracing light visibility instead of precomputed volume-integration caches in NeRFactor | NeRFactor framework · NeRFactor synthetic, view interpolation | PSNR: 30.288 -> 31.194 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · better on 2 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Differentiable Neural Surface Refinement for Modeling Transparent Objects (CVPR 2024 · similarity 0.87)
- Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion (CVPR 2025 · similarity 0.86)
- Eclipse: Disambiguating Illumination and Materials using Unintended Shadows (CVPR 2024 · similarity 0.86)
- SpecNeRF: Gaussian Directional Encoding for Specular Reflections (CVPR 2024 · similarity 0.86)
- ReCap: Better Gaussian Relighting with Cross-Environment Captures (CVPR 2025 · similarity 0.86)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (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.
