Research map / Video / Video segmentation and tracking
Inter-Photon-Limited Videography
Andrew Xie, Dongyu Du, Sotiris Nousias, David B. Lindell, Kiriakos N. Kutulakos
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 Neural Flux Fields instead of bit2bit | video reconstruction · drill sequence, thinned | visual quality (qualitative): fp 2.82 original; bit2bit blurs at fp 1995 and 32359 | Improved |
| use Neural Flux Fields instead of QBP | video reconstruction · guitar sequence, thinned | visual quality (qualitative): fp 4.21 and 21.07 | Improved |
| use Neural Flux Fields instead of UWB | video reconstruction · fan 54 Hz, 40 photons/pixel/s | visual quality (qualitative): fp 44.7 and 5188 | Improved |
| add computational stroboscopy to NFF | Neural Flux Fields · free-running SPAD fan timestamps | visual quality (qualitative) | Improved |
| thin photons to raise fp by 1000x | Neural Flux Fields · foam bullet scene | observability of small fast object: fp 0.447 -> 309 | Hurt |
Closest papers by meaning
- Spatiotemporal Flux Probing for Single-Photon Videography (ECCV 2026 · similarity 0.91)
- Passive Ultra-Wideband Single-Photon Imaging (ICCV 2023 · similarity 0.90)
- Towards 3D Vision with Low-Cost Single-Photon Cameras (CVPR 2024 · similarity 0.85)
- Separating the Wheat from the Chaff: Spatio-Temporal Transformer with View-interweaved Attention for Photon-Efficient Depth Sensing (AAAI 2025 · similarity 0.84)
- Neural Inverse Rendering from Propagating Light (CVPR 2025 · similarity 0.84)
- Image Reconstruction from Readout-Multiplexed Single-Photon Detector Arrays (CVPR 2025 · 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.
