Research map / Video / Video segmentation and tracking
Spatiotemporal Flux Probing for Single-Photon Videography
Jerry Yan, Matteo Forlivesi, Bowen Tan, Andrew Xie, Siddharth Somasundaram, Sotiris Nousias
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 |
|---|---|---|---|
| probe globally over the full space-time photon volume instead of per-pixel temporal probing (UWB) | single-photon videography · UWB dataset (laser pulse, rotating fan) | photons needed for comparable quality: 30x less light | Improved |
| probe globally instead of per-pixel UWB on periodic fan motion | single-photon videography · SPAD512 rotating fan | photons needed: 10x fewer detected photons | Improved |
| replace QBP align-and-merge local aggregation with global probing | single-photon videography · QBP guitar dataset | reconstruction quality (qualitative): at 0.011 ppp | Improved |
| replace bit2bit self-supervised denoising with global probing | single-photon videography · Mandrill dataset | spatial detail and flicker recovery (qualitative) | Improved |
| add Kalman-filter fusion with intensity frames to event-probing reconstruction (ablation) | event camera videography · DAVIS240C dataset | reconstruction quality (qualitative) | Improved |
| add velocity-aware probing to reconstruct under thinned timestamps | toys dataset · toys dataset with thinning | reconstruction quality (qualitative) | Improved |
| apply to highly nonlinear motion (balloon rupture) with velocity focusing | velocity-selective videography · nonlinear motion scenes | selectivity | Hurt |
Closest papers by meaning
- Separating the Wheat from the Chaff: Spatio-Temporal Transformer with View-interweaved Attention for Photon-Efficient Depth Sensing (AAAI 2025 · similarity 0.86)
- Generalized Event Cameras (CVPR 2024 · similarity 0.86)
- Event Fields: Capturing Light Fields at High Speed, Resolution, and Dynamic Range (CVPR 2025 · similarity 0.85)
- Opportunistic Single-Photon Time of Flight (CVPR 2025 · similarity 0.85)
- bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction (NeurIPS 2024 · similarity 0.85)
- Optical Flow for Spike Camera with Hierarchical Spatial-Temporal Spike Fusion (AAAI 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.
