Research map / Video / Video segmentation and tracking
Unrolled Decomposed Unpaired Learning for Controllable Low-Light Video Enhancement
Lingyu Zhu, Wenhan Yang, Baoliang Chen, Hanwei Zhu, Zhangkai Ni, Qi Mao, Shiqi Wang
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 temporal subnet (b) to stage-1 illumination subnet (ablation) | UDU-Net · SDSD outdoor | warp error: 0.54 -> 0.20 | Improved |
| add temporal subnet (b) to stage-1 illumination subnet (ablation) | UDU-Net · SDSD outdoor | PSNR: 21.29 -> 21.43 | Improved |
| add second-stage illumination subnet (c) (ablation) | UDU-Net · SDSD outdoor | PSNR: 21.43 -> 23.92 PSNR; warp 0.20 -> 0.35 | Mixed |
| add human perception feedback (BRISQUE-selected targets) in stage 2 (ablation) | UDU-Net · SDSD outdoor | PSNR: 21.87 -> 23.94 | Improved |
| add human perception feedback (ablation) | UDU-Net · SDSD outdoor | warp error: 0.14 -> 0.24 | Hurt |
| add human perception feedback (ablation) | UDU-Net · SDSD indoor | PSNR: 22.00 -> 22.41 | Improved |
| reference-free UDU-Net vs second-best reference-free method | UDU-Net · SDSD outdoor | PSNR: gain of 2.05 dB and 0.1158 SSIM | Improved |
| reference-free UDU-Net vs supervised SDSDNet | UDU-Net · SDSD indoor | PSNR: 27.03 vs 22.41 | Hurt |
Closest papers by meaning
- Temporally Consistent Enhancement of Low-Light Videos via Spatial-Temporal Compatible Learning (IJCV 2024 · similarity 0.90)
- Empowering Low-Light Image Enhancer through Customized Learnable Priors (ICCV 2023 · similarity 0.89)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.89)
- Learning Temporal Consistency for Low Light Video Enhancement From Single Images (CVPR 2021 · similarity 0.89)
- Binarized Low-light Raw Video Enhancement (CVPR 2024 · similarity 0.87)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.87)
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.
