Research map / Video / Video segmentation and tracking
Enhancing Low Light Videos by Exploring High Sensitivity Camera Noise
Wei Wang, Xin Chen, Cheng Yang, Xiang Li, Xuemei Hu, Tao Yue
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 the proposed LSTM-based network instead of VBM4D, FFDNet, KPN or TOFlow, all trained on the same noise-model data | low-light video denoising and enhancement · Synthetic low-light videos (Canon 5D noise model) | PSNR/SSIM: at least 2dB/0.05 improvement in PSNR/SSIM | Improved |
| train with the proposed physical high-sensitivity noise model instead of AWGN or Gaussian-Poisson mixture noise (ablation) | TOFlow and the proposed network · Real captured dark videos (Canon 5D) | visual quality (chrominance artifacts, detail, contrast) | Improved |
| train TOFlow with the proposed noise model (ablation) | TOFlow · Synthetic videos, 0.05 to 0.2 Lux | PSNR/SSIM | Improved |
| add more preceding frames in recurrent processing | proposed LSTM network · Per-frame PSNR on a test video | PSNR: PSNR rises frame by frame, flat after about 20 frames | Mixed |
Closest papers by meaning
- Learning to Restore Low-Light Images via Decomposition-and-Enhancement (CVPR 2020 · similarity 0.89)
- Unrolled Decomposed Unpaired Learning for Controllable Low-Light Video Enhancement (ECCV 2024 · similarity 0.88)
- Contrastive Learning for Low-Light Raw Denoising (Student Abstract) (AAAI 2024 · similarity 0.88)
- Physics-based Noise Modeling for Extreme Low-light Photography (TPAMI 2021 · similarity 0.87)
- Binarized Low-light Raw Video Enhancement (CVPR 2024 · similarity 0.87)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.86)
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.
