Research map / Architectures and efficiency / CNN design
RainFlow: Optical Flow Under Rain Streaks and Rain Veiling Effect
Ruoteng Li, Robby T. Tan, Loong-Fah Cheong, Angelica I. Aviles-Rivero, Qingnan Fan, Carola-Bibiane Schonlieb
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 feature multiplier M to PWC-Net-style model (ablation) | PWC-rain · Sintel (rain) | EPE: 7.26 -> 6.27 | Improved |
| add feature multiplier M (ablation) | PWC-rain · VKITTI (rain) | EPE: 9.69 -> 8.96 | Improved |
| add feature multiplier M (ablation) | PWC-rain · Sintel (clean) | EPE: 4.46 -> 3.67 | Improved |
| add chromatic pyramids with invariant feature mapping (ablation) | PWC-rain · Sintel (rain) | EPE: 7.26 -> 6.03 | Improved |
| add chromatic pyramids with invariant feature mapping (ablation) | PWC-rain · VKITTI (clean) | EPE: 9.40 -> 6.75 | Improved |
| add chromatic pyramids with invariant feature mapping (ablation) | PWC-rain · VKITTI (rain) | EPE: 9.69 -> 9.38 | Improved |
| combine both M and chromatic pyramids (full RainFlow) (ablation) | Ours w/o M · Sintel (rain) | EPE: 6.27 -> 4.59 | Improved |
| combine both M and chromatic pyramids (full RainFlow) (ablation) | Ours w/o ChromPyrd · VKITTI (rain) | EPE: 9.38 -> 8.27 | Improved |
| train PWC-Net on rain data | PWC-Net · Sintel (clean) | EPE: 2.55 -> 4.46 | Hurt |
| train FlowNet2 on rain data | FlowNet2 · Sintel (clean) | EPE: 2.02 -> 4.65 | Hurt |
| train PWC-Net on rain data | PWC-Net · Sintel (rain) | EPE: 14.20 -> 7.26 | Improved |
| apply deraining preprocessing before flow | Robust-Flow · FVR-660 | EPE: 1.76 -> 1.80 | No clear effect |
Closest papers by meaning
- Deep Joint Rain Detection and Removal From a Single Image (CVPR 2017 · similarity 0.91)
- Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (TPAMI 2019 · similarity 0.91)
- Depth-Attentional Features for Single-Image Rain Removal (CVPR 2019 · similarity 0.90)
- Joint Bi-Layer Optimization for Single-Image Rain Streak Removal (ICCV 2017 · similarity 0.90)
- Rethinking Image Deraining via Rain Streaks and Vapors (ECCV 2020 · similarity 0.90)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.90)
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.
