Research map / Image generation / Image restoration
Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks
Sixiang Chen, Tian Ye, Jinbin Bai, Erkang Chen, Jun Shi, Lei Zhu
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 |
|---|---|---|---|
| replace window self-attention with sparse sampling attention (ablation) | UDR-S2Former · RainDS-Syn RDS | PSNR: 36.15 -> 36.91 | Improved |
| replace ART sparse attention with sparse sampling attention (ablation) | UDR-S2Former · RainDS-Syn RDS | PSNR: 36.39 -> 36.91 | Improved |
| replace channel self-attention with sparse sampling attention (ablation) | UDR-S2Former · RainDS-Syn RDS | PSNR: 36.23 -> 36.91 | Improved |
| add uncertainty-driven constraint to sparse sampling attention (ablation) | UDR-S2Former · RainDS-Syn RDS | PSNR: 36.25 -> 36.91 | Improved |
| add ranking strategy to sparse sampling attention (ablation) | UDR-S2Former · RainDS-Syn RDS | PSNR: 36.29 -> 36.91 | Improved |
| add uncertainty to local reconstruction (ablation) | UDR-S2Former · RainDS-Syn RDS | PSNR: 36.33 -> 36.91 | Improved |
| add ranking strategy to local reconstruction (ablation) | UDR-S2Former · RainDS-Syn RDS | PSNR: 36.45 -> 36.91 | Improved |
| UDR-S2Former versus IDT on Rain200H | image deraining · Rain200H | PSNR: 32.10 -> 32.59 | Improved |
| UDR-S2Former versus IDT on AGAN-Data | raindrop removal · AGAN-Data | PSNR: 31.63 -> 32.64 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GIQE: Generic Image Quality Enhancement via Nth Order Iterative Degradation (CVPR 2022 · similarity 0.89)
- Simultaneous Fidelity and Regularization Learning for Image Restoration (TPAMI 2019 · similarity 0.89)
- Towards Universal Rainy Image Restoration: Benchmark and Baseline (AAAI 2025 · similarity 0.88)
- Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining (CVPR 2024 · similarity 0.88)
- MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery (NeurIPS 2025 · similarity 0.88)
- Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration (CVPR 2024 · 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.
