Research map / 3D vision / Depth and stereo
Seeing Far in the Dark with Patterned Flash
Zhanghao Sun, Jian Wang, Yicheng Wu, Shree Nayar
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 patterned flash instead of uniform flash at long distance | Flash imaging · Synthetic FlyingThings3D scenes, 128 test scenes | image reconstruction quality | Improved |
| use patterned flash instead of uniform flash at close range (<8) | Flash imaging · Synthetic scenes | image reconstruction quality | Hurt |
| use patterned flash instead of uniform flash in pixel-binned captured input | Flash imaging · Synthetic scenes | input SNR gain: about 6 dB gain vs 12dB (4x) upper bound | Improved |
| add a nonzero baseline between camera and flash (ablation) | Patterned flash · Synthetic scenes | image reconstruction quality | No clear effect |
| use pseudo-random dot pattern instead of regular pattern (ablation) | Patterned flash · Synthetic scenes | image reconstruction quality | Hurt |
| use patterned flash instead of uniform flash for face detection | Reconstructed images · Real-world face detection (MediaPipe) | face detection success | Improved |
| change baseline between camera and projector (0 to 2cm) (ablation) | Patterned flash prototype · Real-world captures | image reconstruction quality | No clear effect |
Closest papers by meaning
- Seeing in Extra Darkness Using a Deep-Red Flash (CVPR 2021 · similarity 0.89)
- Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments (CVPR 2021 · similarity 0.85)
- Computational Flash Photography Through Intrinsics (CVPR 2023 · similarity 0.85)
- Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation (CVPR 2025 · similarity 0.84)
- Event Fields: Capturing Light Fields at High Speed, Resolution, and Dynamic Range (CVPR 2025 · similarity 0.83)
- SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream (CVPR 2024 · similarity 0.81)
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.
