Research map / 3D vision / Depth and stereo
Panoramas from Photons
Sacha Jungerman, Atul Ingle, Mohit Gupta
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 |
|---|---|---|---|
| add stratified re-sampling of virtual exposures with midpoint-centered overlapping groups (ablation) | Panoramas from Photons · SPAD panorama reconstruction | visual quality (blur, ghosting) | Improved |
| run a second refinement iteration (ablation) | Panoramas from Photons · SPAD panorama reconstruction | visual quality (sharpness, distortion) | Improved |
| aggregate binary frames from a single-photon camera instead of conventional RGB frames | panorama pipeline · simulated low-light fast motion | reconstruction success | Improved |
| use larger group size m for low light (ablation) | Panoramas from Photons · SPAD panorama reconstruction | noise vs motion blur tradeoff | Mixed |
| apply method to a commercial high-speed camera (Infinicam) instead of SPAD | Panoramas from Photons · real capture | reconstruction quality | Mixed |
| second-pass method vs one-shot QBP motion compensation | Panoramas from Photons · SPAD capture, group size m=1000 | visual sharpness | Improved |
| street light flicker violates brightness constancy | Panoramas from Photons · night scene with artificial lighting | reconstruction success | Hurt |
Closest papers by meaning
- Eulerian Single-Photon Vision (ICCV 2023 · similarity 0.89)
- SoDaCam: Software-defined Cameras via Single-Photon Imaging (ICCV 2023 · similarity 0.89)
- Towards 3D Vision with Low-Cost Single-Photon Cameras (CVPR 2024 · similarity 0.86)
- bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction (NeurIPS 2024 · similarity 0.85)
- Generalized Event Cameras (CVPR 2024 · similarity 0.85)
- Event Fields: Capturing Light Fields at High Speed, Resolution, and Dynamic Range (CVPR 2025 · similarity 0.85)
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.
