Research map / 3D vision / Depth and stereo
Imaging Behind Occluders Using Two-Bounce Light
Connor Henley, Tomohiro Maeda, Tristan Swedish, Ramesh Raskar
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 |
|---|---|---|---|
| replace naive carving with probabilistic robust carving (outside and inside count thresholds) (ablation) | Two-bounce space carving · Mannequin behind occluder, non-planar relay surfaces | reconstruction quality (qualitative) | Improved |
| add inside tests (require N>0 inside results to accept a voxel) (ablation) | Naive carving · Mannequin behind occluder, 30 illumination spots | false positives at grid periphery (qualitative) | Improved |
| reduce number of scan points to four shadows per frame | Two-bounce space carving · Moving mannequin video | reconstruction detail vs frame rate: 15 FPS, four shadows, .27 seconds per scan | Mixed |
Closest papers by meaning
- Using Unknown Occluders to Recover Hidden Scenes (CVPR 2019 · similarity 0.87)
- Trapping Light for Time of Flight (CVPR 2018 · similarity 0.86)
- Efficient Non-Line-of-Sight Imaging from Transient Sinograms (ECCV 2020 · similarity 0.86)
- Inferring Light Fields From Shadows (CVPR 2018 · similarity 0.86)
- Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients (NeurIPS 2024 · similarity 0.85)
- PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar (CVPR 2024 · 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.
