Research map / Image generation / Super-resolution
Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-Based Super-resolution
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use AMSA-rec instead of C²-Matching-rec | Reference-based super-resolution · CUFED5 | PSNR: 28.24 -> 28.50 | Helped |
| Use AMSA-rec instead of C²-Matching-rec | Reference-based super-resolution · Sun80 | PSNR: 30.18 -> 30.29 | Helped |
| Use AMSA-rec instead of MASA-rec | Reference-based super-resolution · Urban100 | PSNR: 26.09 -> 26.18 | Helped |
| Use AMSA-rec instead of C²-Matching-rec | Reference-based super-resolution · Manga109 | PSNR: 30.47 -> 30.57 | Helped |
| Add MSDA (ablation) | AMSA with CFE-PatchMatch · CUFED5 | PSNR: 28.21 -> 28.50 | Helped |
| Replace CFE-PatchMatch with enumerated matching (ablation) | AMSA with MSDA · CUFED5 | PSNR: 28.50 -> 28.51 | No clear effect |
| Replace CFE-PatchMatch with enumerated matching (ablation) | AMSA with MSDA · CUFED5 | GFLOPs: 279.52 -> 29297.82 | Hurt |
| Replace CFE-PatchMatch with MEM (ablation) | AMSA with MSDA · CUFED5 | PSNR: 28.43 -> 28.50 | Hurt |
| Replace CFE-PatchMatch with MEM (ablation) | AMSA with MSDA · CUFED5 | GFLOPs: 1479.87 -> 279.52 | Hurt |
| Apply matching iterations coarse-to-fine (ablation) | Embedded PatchMatch · CUFED5 matching convergence | MSE | Helped |
| Use Dynamic Aggregation (ablation) | MSDA · CUFED5 with minor scale misalignment | super-resolution performance | Helped |
| Use Multi-Scale Aggregation (ablation) | MSDA · CUFED5 with large scale misalignment | super-resolution performance | Helped |
Closest papers by meaning
- Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World (CVPR 2024 · similarity 0.85)
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · similarity 0.85)
- Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution (CVPR 2024 · similarity 0.84)
- SinSR: Diffusion-Based Image Super-Resolution in a Single Step (CVPR 2024 · similarity 0.84)
- DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF (CVPR 2024 · similarity 0.84)
- PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors (NeurIPS 2025 · similarity 0.84)
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.