Research map / Image generation / Super-resolution
ReAL: Reference-to-Image (R2I) Aware Latent Diffusion for Image Super-Resolution
Byeonghun Lee, Hyunmin Cho, Sunghoon Im, Kyong Hwan Jin
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 the LR-latent concatenation path (ablation) | ReAL · SR x4 ablation | PSNR: 26.689 -> 27.352 | Improved |
| add the LR-latent concatenation path (ablation) | ReAL · SR x4 ablation | LPIPS: 0.309 -> 0.246 | Improved |
| add reference conditioning (ablation) | ReAL · SR x4 ablation | SSIM: 0.799 -> 0.803 | Improved |
| add reference conditioning (ablation) | ReAL · SR x4 ablation | LPIPS: 0.250 -> 0.246 | Improved |
| add reference conditioning (ablation) | ReAL · SR x4 ablation | PSNR: 27.084 -> 27.352 | Hurt |
| add the Reference Fusion Module (ablation) | ReAL · SR x4 ablation | PSNR: 26.837 -> 27.352 | Improved |
| add the Reference Fusion Module (ablation) | ReAL · SR x4 ablation | MUSIQ: 61.802 -> 61.565 | Mixed |
| use a properly retrieved reference instead of a random one (ablation) | ReAL · SR x4 ablation | SSIM: 0.780 -> 0.803 | Improved |
| use a properly retrieved reference instead of a random one (ablation) | ReAL · SR x4 ablation | LPIPS: 0.263 -> 0.246 | Improved |
| increase reference database from 30% to 100% (ablation) | ReAL · RealSR | MUSIQ: 61.240 -> 66.529 | Improved |
| use external CUFED database instead of in-domain database (ablation) | ReAL · RealSR | PSNR: 21.044 -> 21.060 | No clear effect |
| use learned hashing instead of VGG retrieval (ablation) | ReAL · reference matching | matching cost (ms): 3830 ms -> 62 ms | 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.
- CoSeR — CoSeR: Bridging Image and Language for Cognitive Super-Resolution (CVPR 2024) · better on 3 of 3 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
- SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution (CVPR 2024 · similarity 0.90)
- When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution (NeurIPS 2026 · similarity 0.90)
- Text-guided Explorable Image Super-resolution (CVPR 2024 · similarity 0.90)
- Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach (CVPR 2025 · similarity 0.90)
- TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution (CVPR 2025 · similarity 0.90)
- RAP-SR: RestorAtion Prior Enhancement in Diffusion Models for Realistic Image Super-Resolution (AAAI 2025 · similarity 0.89)
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.
