Research map / Image generation / Super-resolution
Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework
Enzhuo Zhang, Sijie Zhao, Dilxat Muhtar, Zhenshi Li, Xueliang Zhang, Pengfeng Xiao
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 RTDM as spatial condition (ablation) | TexADiff · AID | PSNR: 21.86 -> 22.58 | Improved |
| add RTDM as spatial condition (ablation) | TexADiff · AID | LPIPS: 0.4173 -> 0.4023 | Improved |
| add TADL loss on top of RTDM condition (ablation) | TexADiff · AID | LPIPS: 0.4023 -> 0.3887 (w/o TA-sampling) | Improved |
| add texture-aware sampling schedule (ablation) | TexADiff · AID | LPIPS: 0.3887 -> 0.3883 | Improved |
| use ground-truth RTDM instead of predicted (ablation) | TexADiff · AID | LPIPS: 0.3823 -> 0.3493 | Improved |
| invert predicted RTDM (ablation) | TexADiff · AID | LPIPS: 0.3823 -> 0.4305 | Hurt |
| use all-zeros mask instead of predicted RTDM (ablation) | TexADiff · AID | PSNR: 22.62 -> 23.70 | Mixed |
| unfreeze first down block and all up blocks vs cross-attention only (ablation) | TexADiff · AID | LPIPS: 0.6001 -> 0.3883 | Improved |
| unfreeze first down block and all up blocks vs Down+Mid (ablation) | TexADiff · AID | LPIPS: 0.4097 -> 0.3883 | Improved |
| binarize the RTDM (ablation) | TexADiff · AID | PSNR: 19.02 -> 22.78 | Improved |
| use TexADiff instead of FaithDiff for downstream segmentation | SR then DeepLabV3+ · LoveDA | mIoU: 40.25 -> 44.06 | Improved |
| use TexADiff instead of FaithDiff | SDXL-based SR · 1024x1024 inference | inference time (s): 7.8 -> 9.0 | Hurt |
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.
- FaithDiff — FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution (CVPR 2025) · better on 7 of 9 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
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · similarity 0.89)
- BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution (AAAI 2025 · similarity 0.88)
- Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs (NeurIPS 2024 · similarity 0.87)
- SinSR: Diffusion-Based Image Super-Resolution in a Single Step (CVPR 2024 · similarity 0.87)
- SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening (NeurIPS 2024 · similarity 0.86)
- TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution (CVPR 2025 · similarity 0.85)
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.
