Research map / 3D vision / Depth and stereo
Single-Photon 3D Imaging with Equi-Depth Photon Histograms
Kaustubh Sadekar, David Maier, Atul Ingle
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 fixed-stepping binner (HEDH) with optimized proportional binner (PEDH) | equi-depth histogram distance estimation · NYUv2 test, narrowest-bin estimator | RMSE (cm): 219.91 -> 18.05 | Improved |
| add DeePEDH neural network on top of PEDH boundaries | PEDH 32-bin · NYUv2 test | RMSE (cm): 18.05 -> 10.92 | Improved |
| use equi-depth bins instead of equi-width bins at the same 32-bin memory | single-photon distance estimation · NYUv2 test | RMSE (cm): 29.80 -> 10.92 | Improved |
| use 32-bin DeePEDH instead of 1024-bin EWH | single-photon distance estimation · NYUv2 test | RMSE (cm): 6.89 -> 10.92 | Hurt |
| use linear-interpolation estimator instead of narrowest-bin estimator with PEDH (ablation) | PEDH · single-pixel simulation | mean absolute error: increase of about 0.1 cm | Hurt |
| increase step-size scaling factor K with no decay or smoothing (ablation) | proportional binner · binner simulation | boundary and distance RMSE | Hurt |
| optimized stepping versus fixed stepping binner | median-tracking binner · background flux 5.0 simulation | CV RMSE: 10.13 -> 4.06 | Improved |
| DeePEDH versus 1024-bin EWH on Middlebury (out-of-distribution) | DeePEDH · Middlebury test | RMSE (cm): 2.00 -> 2.56 | Hurt |
| PEDH versus HEDH on real hardware data under high background flux | PEDH · Gupta et al. hardware dataset | RMSE (cm): 153.8 -> 17.2 at background 5.0 | Improved |
Closest papers by meaning
- Count-Free Single-Photon 3D Imaging With Race Logic (TPAMI 2023 · similarity 0.95)
- Towards 3D Vision with Low-Cost Single-Photon Cameras (CVPR 2024 · similarity 0.88)
- Compressive Single-Photon 3D Cameras (CVPR 2022 · similarity 0.88)
- Separating the Wheat from the Chaff: Spatio-Temporal Transformer with View-interweaved Attention for Photon-Efficient Depth Sensing (AAAI 2025 · similarity 0.85)
- Opportunistic Single-Photon Time of Flight (CVPR 2025 · similarity 0.84)
- 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.
