Research map / Video / Video segmentation and tracking
Seeing in Extra Darkness Using a Deep-Red Flash
Jinhui Xiong, Jian Wang, Wolfgang Heidrich, Shree Nayar
Check 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 guide-signal modulation during training (ablation) | MFF-Net · Validation images | PSNR: 23.82 -> 26.89 | Improved |
| add L2 loss to VGG perceptual loss (ablation) | MFF-Net with guide-signal modulation · Validation images | PSNR: 26.73 -> 26.89 | Improved |
| fuse no-flash frames with deep-red-flash guide frames | Ours · 0.2 lux, 8-bit raw | PSNR: 18.2 -> 22.8 | Improved |
| fuse no-flash frames with deep-red-flash guide frames | Ours · 0.4 lux, 8-bit raw | PSNR: 21.7 -> 24.4 | Improved |
| fuse no-flash frames with deep-red-flash guide frames | Ours · 0.05 lux, 12-bit raw | PSNR: 17.7 -> 20.9 | Improved |
| fuse no-flash frames with deep-red-flash guide frames | Ours · 0.1 lux, 12-bit raw | PSNR: 20.6 -> 23.8 | Improved |
| fuse no-flash frames with deep-red-flash guide frames | Ours · 0.2 lux, 12-bit raw | PSNR: 23.0 -> 25.6 | Improved |
| fuse no-flash frames with deep-red-flash guide frames | Ours · 0.4 lux, 12-bit raw | PSNR: 25.6 -> 28.2 | Improved |
| use temporal consistency enhancement with TCE-Net | Mesopic flash videography pipeline · Video reconstruction | temporal warping error: 15% | Improved |
Closest papers by meaning
- Seeing Far in the Dark with Patterned Flash (ECCV 2022 · similarity 0.89)
- Learning to See Moving Objects in the Dark (ICCV 2019 · similarity 0.86)
- Seeing Motion in the Dark (ICCV 2019 · similarity 0.86)
- Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments (CVPR 2021 · similarity 0.86)
- Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images (AAAI 2025 · similarity 0.84)
- Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset (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.
