Research map / Video / Video segmentation and tracking
VSRELL: A Simple Baseline for Video Super-Resolution and Enhancement in Low-Light Environment
Yanming Hui, Fanhua Shang, Hongying Liu, Ben Wang, Zhenwei Zhang, Liang Wan, Wei Feng, Tong Xue, Bingqin Lv
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 INCO illumination-noise co-optimization (ablation) | VSRELL baseline · REDS4 | PSNR: 23.15 -> 24.91 | Improved |
| add INCO illumination-noise co-optimization (ablation) | VSRELL baseline · REDS4 | SSIM: 0.761 -> 0.769 | Improved |
| add ISFP illumination-sensitive propagation (ablation) | VSRELL baseline · REDS4 | PSNR: 23.15 -> 25.07 | Improved |
| add ISFP illumination-sensitive propagation (ablation) | VSRELL baseline · REDS4 | SSIM: 0.761 -> 0.765 | Improved |
| combine INCO and ISFP (ablation) | VSRELL baseline · REDS4 | PSNR: 23.15 -> 25.94 | Improved |
| combine INCO and ISFP (ablation) | VSRELL baseline · REDS4 | parameters and MACs: 5.283 M -> 6.287 M | Hurt |
| use window size 3 instead of 1 (ablation) | VSRELL · REDS4 clip 011 frame 011 | PSNR (dB): 24.64 -> 25.43 | Improved |
| use window size 5 instead of 3 (ablation) | VSRELL · REDS4 clip 011 frame 011 | PSNR (dB): 25.43 -> 25.37 | No clear effect |
| use window size 7 instead of 3 (ablation) | VSRELL · REDS4 clip 011 frame 011 | PSNR (dB): 25.43 -> 23.92 | Hurt |
| jointly model enhancement and SR instead of cascading best cascade | VSRELL · REDS4 | PSNR: 20.64 -> 25.94 | Improved |
| joint model vs retrained all-in-one methods | VSRELL · REDS4 | PSNR: 19.30 -> 25.94 | Improved |
Closest papers by meaning
- SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation (ECCV 2026 · similarity 0.87)
- Real-World Video Super-Resolution: A Benchmark Dataset and a Decomposition Based Learning Scheme (ICCV 2021 · similarity 0.87)
- VideoGigaGAN: Towards Detail-rich Video Super-Resolution (CVPR 2025 · similarity 0.87)
- Turning Frequency to Resolution: Video Super-Resolution via Event Cameras (CVPR 2021 · similarity 0.87)
- Investigating Tradeoffs in Real-World Video Super-Resolution (CVPR 2022 · similarity 0.87)
- Learning Trajectory-Aware Transformer for Video Super-Resolution (CVPR 2022 · 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.
