Research map / Image generation / Super-resolution
Towards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation
Xu Yan, Weibing Zhao, Kun Yuan, Ruimao Zhang, Zhen Li, Shuguang Cui
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 single-patch swapping with multi-reference LFE aggregation (CIMR-l2 vs SRNTT-l2) | reference SR · Sun80 | PSNR (dB): 28.54 -> 30.07 | Improved |
| replace SRNTT-l2 with CIMR-l2 using content-independent references | reference SR · CUFED5 | PSNR (dB): 26.24 -> 26.35 | Improved |
| replace SRNTT-l2 with CIMR-l2 on Urban100 | reference SR · Urban100 | PSNR (dB): 25.50 -> 25.77 | Improved |
| replace SRNTT-l2 with CIMR-l2 given level-1 similar references | reference SR · CUFED5 L1 | PSNR (dB): 26.15 -> 27.32 | Improved |
| replace SRNTT with CIMR (GAN) on HR (warp) references | reference SR · CUFED5 HR (warp) | PSNR (dB): 33.87 -> 30.73 | Hurt |
| add key features from conv1, conv2 and conv3 instead of conv3 only (ablation) | CIMR-l2 · CUFED5 L1 | PSNR (dB): 26.26 -> 27.32 | Improved |
| add key features from conv1, conv2 and conv3 instead of conv2 only (ablation) | CIMR-l2 · CUFED5 L1 | PSNR (dB): 27.06 -> 27.32 | Improved |
| add conv1 and conv3 key features to conv2 key features (ablation) | CIMR-l2 · CUFED5 feature searching time | seconds per sample: 1.551 -> 4.616 | Hurt |
| use conv3 key features only instead of SRNTT patch swapping (ablation) | CIMR-l2 · CUFED5 feature searching time | seconds per sample: 2.726 -> 1.020 | Improved |
Closest papers by meaning
- Task Decoupled Framework for Reference-Based Super-Resolution (CVPR 2022 · similarity 0.91)
- LMR: A Large-Scale Multi-Reference Dataset for Reference-Based Super-Resolution (ICCV 2023 · similarity 0.91)
- Robust Reference-Based Super-Resolution via C2-Matching (CVPR 2021 · similarity 0.90)
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · similarity 0.85)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.85)
- Block-Based Multi-Scale Image Rescaling (AAAI 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.
