Research map / Image generation / Super-resolution
PlantRSR: A New Plant Dataset and Method for Reference-based Super-Resolution
Hongyang Zhou, Xiaobin Zhu, Shengxiang Yu, Liuling Chen, Jingyan Qin, Xu-Cheng Yin
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 diffusion module to TGDM (ablation) | TGDM · PlantRSR test | PSNR: 38.52 -> 38.62 | Improved |
| TGDM instead of RFA texture fusion (ablation) | SKRM+TGDM · PlantRSR test | PSNR: 38.48 -> 38.62 | Improved |
| TGDM instead of DA texture fusion (ablation) | SKRM+TGDM · PlantRSR test | PSNR: 38.43 -> 38.62 | Improved |
| SKRM matching instead of MEM (ablation) | SKRM · PlantRSR test | PSNR: 38.36 -> 38.62 | Improved |
| SKRM instead of exhaustive enumerated matching (ablation) | SKRM · matching cost | GFLOPs: 11990.39 -> 77.86 | Improved |
| SKRM instead of enumerated matching (ablation) | SKRM · PlantRSR test | PSNR: 38.62 -> 38.62 | No clear effect |
| train on PlantRSR instead of CUFED5 (ablation) | Ours · PlantRSR test | PSNR: 38.40 -> 38.62 | Improved |
| train on PlantRSR instead of DRefSR (ablation) | Ours · PlantRSR test | PSNR: 38.49 -> 38.62 | Improved |
| train SSMTF on PlantRSR instead of CUFED5 (ablation) | SSMTF · PlantRSR test | PSNR: 38.28 -> 38.49 | Improved |
| increase sampling steps from 1 to 4 (ablation) | TGDM · Fine veins texture | PSNR: 27.62 -> 28.04 | Improved |
| increase sampling steps from 4 to 8 (ablation) | TGDM · Fine veins texture | PSNR: 28.04 -> 28.07 | No clear effect |
| increase sampling steps from 4 to 8 (ablation) | TGDM · Thick stems texture | PSNR: 37.32 -> 37.34 | No clear effect |
Closest papers by meaning
- LMR: A Large-Scale Multi-Reference Dataset for Reference-Based Super-Resolution (ICCV 2023 · similarity 0.87)
- Image Super-Resolution by Neural Texture Transfer (CVPR 2019 · similarity 0.87)
- Task Decoupled Framework for Reference-Based Super-Resolution (CVPR 2022 · similarity 0.87)
- Robust Reference-Based Super-Resolution via C2-Matching (CVPR 2021 · similarity 0.86)
- MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution (CVPR 2021 · similarity 0.86)
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · 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.
