Research map / 3D vision / Face and shape
NLOS-NeuS: Non-line-of-sight Neural Implicit Surface
Yuki Fujimura, Takahiro Kushida, Takuya Funatomi, Yasuhiro Mukaigawa
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 |
|---|---|---|---|
| extend NeTF with an SDF and volume rendering (NLOS-NeuS) | NeTF · Synthetic bunny | Depth RMSE (cm): 8.26 -> 4.63 | Improved |
| NLOS-NeuS versus DLCT discretized representation | NLOS-NeuS · Synthetic bunny | Depth MAE (cm): 1.59 (DLCT) vs 1.84 | Mixed |
| NLOS-NeuS continuous representation versus DLCT on real captures | NLOS-NeuS · Real SPAD captures (f-k dataset) | surface quality (qualitative) | Improved |
| add zero signed-distance self-supervision (L_z) and entropy weight loss (L_en) (ablation) | NLOS-NeuS · Synthetic bunny | shape completeness (qualitative) | Improved |
| add only L_z or only L_en (ablation) | NLOS-NeuS · Synthetic bunny | shape near object boundary | Mixed |
| add entropy loss L_en to constrain alpha (ablation) | NLOS-NeuS · Synthetic bunny | alpha convergence | Improved |
| add first-returning-photon lower bound loss (L_f) (ablation) | NLOS-NeuS · Synthetic bunny | overall geometry accuracy (qualitative) | Improved |
| use SDF for non-closed or thin structures | NLOS-NeuS · Two-plane and thin-structure scenes | geometry (qualitative) | Hurt |
Closest papers by meaning
- Non-line-of-Sight Imaging via Neural Transient Fields (TPAMI 2021 · similarity 0.90)
- Non-Line-of-Sight Imaging With Signal Superresolution Network (CVPR 2023 · similarity 0.89)
- Beyond Volumetric Albedo -- A Surface Optimization Framework for Non-Line-Of-Sight Imaging (CVPR 2019 · similarity 0.89)
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021 · similarity 0.88)
- From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS (NeurIPS 2024 · similarity 0.87)
- Dual-branch Graph Feature Learning for NLOS Imaging (AAAI 2025 · similarity 0.85)
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.
