Research map / 3D vision / Depth and stereo
The Geometry of First-Returning Photons for Non-Line-Of-Sight Imaging
Check 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 |
|---|---|---|---|
| Use first-returning photon path lengths to carve out ellipsoidal free space | NLOS space carving · Simulated bunny scene | NLOS scene volume: 5.56 -> 0.44 | Helped |
| Estimate shape from first-returning photons across varying scene reflectances (ablation) | First-returning photon shape recovery · Simulated sphere with three reflectance settings | recovered point geometry | No clear effect |
| Increase the noise level (ablation) | First-returning photon shape recovery · Simulated sphere | scene point recovery error | Hurt |
| Increase the local neighborhood size for the mirror-image estimate (ablation) | First-returning photon shape recovery · Simulated sphere | scene point recovery error | Mixed |
| Use first-returning photons to recover scene points and normals | NLOS shape recovery · Simulated sphere | normal recovery error: < 0.1° | Helped |
| Use thresholding to select first-returning photons instead of extracting peaks from the transient (ablation) | Real-scene NLOS shape recovery · SPAD real-scene dataset | scene point coverage | Hurt |
| Extract and cluster peaks from the light transient to select returns from additional surfaces (ablation) | Real-scene NLOS shape recovery · SPAD real-scene dataset | scene point coverage | Helped |
Closest papers by meaning
- Beyond Volumetric Albedo -- A Surface Optimization Framework for Non-Line-Of-Sight Imaging (CVPR 2019 · similarity 0.91)
- Towards 3D Vision with Low-Cost Single-Photon Cameras (CVPR 2024 · similarity 0.87)
- Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients (NeurIPS 2024 · similarity 0.86)
- PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar (CVPR 2024 · similarity 0.84)
- Opportunistic Single-Photon Time of Flight (CVPR 2025 · similarity 0.83)
- Dual-branch Graph Feature Learning for NLOS Imaging (AAAI 2025 · similarity 0.83)
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.