Research map / 3D vision / Depth and stereo
Optimal LED Spectral Multiplexing for NIR2RGB Translation
Lei Liu, Yuze Chen, Junchi Yan, Yinqiang Zheng
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 |
|---|---|---|---|
| Select an LED multiplexing with target-loss minimization rather than use a random LED combination (ablation) | NIR2RGB translation on ICVL · ICVL | PSNR (dB): 22.94 -> 24.53 | Improved |
| Select an LED multiplexing with target-loss minimization rather than use an 850nm LED | NIR2RGB translation on ICVL · ICVL | PSNR (dB): 22.01 -> 24.53 | Improved |
| Select an LED multiplexing with target-loss minimization rather than use a 940nm LED | NIR2RGB translation on ICVL · ICVL | PSNR (dB): 21.85 -> 24.53 | Improved |
| Use target-loss minimization (TLM) rather than RGB-variance maximization (RVM) for LED selection | NIR2RGB translation · ICVL, 15S5C | PSNR: 24.2054 -> 24.5263 | Improved |
| Use target-loss minimization (TLM) rather than RGB-variance maximization (RVM) for LED selection | NIR2RGB translation · TokyoTech, 15S5C | PSNR: 16.5380 -> 16.3309 | Hurt |
| Use target-loss minimization (TLM) rather than RGB-variance maximization (RVM) for LED selection | NIR2RGB translation · IDH, 15S5C | PSNR: 26.0707 -> 25.0017 | Hurt |
| Add an LED selection module instead of using a random LED combination (ablation) | NIR2RGB translation on ICVL · ICVL | RMSE: 8.30 -> 7.74 | Improved |
Closest papers by meaning
- Visibility Constrained Wide-Band Illumination Spectrum Design for Seeing-in-the-Dark (CVPR 2023 · similarity 0.87)
- Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images (AAAI 2025 · similarity 0.82)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.81)
- Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning (CVPR 2024 · similarity 0.81)
- DarkIR: Robust Low-Light Image Restoration (CVPR 2025 · similarity 0.80)
- Cross-spectral Gated-RGB Stereo Depth Estimation (CVPR 2024 · similarity 0.80)
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.
