Research map / Image generation / Super-resolution
Low-Resolution Editing is All You Need for High-Resolution Editing
Junsung Lee, Hyunsoo Lee, Yong Jae Lee, Bohyung Han
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 |
|---|---|---|---|
| Use detail-transfer editing on high-res source instead of low-res edit plus super-resolution | ScaleEdit (SD 2.1) · 2K-editing | HaarPSI: 0.316 -> 0.331 vs DiT-SR | Improved |
| Same comparison on masked SSIM | ScaleEdit (SD 2.1) · 2K-editing | M-SSIM: 0.755 -> 0.806 vs PiSA-SR | Improved |
| Same comparison at 1K | ScaleEdit (SD 2.1) · 1K-editing | LPIPS: 0.465 -> 0.460 vs PiSA-SR | Improved |
| Compare against PiSA-SR on LPIPS at 2K | ScaleEdit (SD 2.1) · 2K-editing | LPIPS: 0.472 (PiSA-SR) vs 0.496 | Hurt |
| Add patch synchronization (blended Tweedie plus resampling) (ablation) | ScaleEdit · 2K-editing | visual seams | Improved |
| Use 1x1 conv transfer function instead of learnable constant vector (ablation) | ScaleEdit · cat-to-dog edits | qualitative | Improved |
| Swap backbone to FLUX.1-dev | ScaleEdit · 1K-editing | qualitative | Improved |
| Scale to 8K editing without extra tuning | ScaleEdit · 8K-editing | qualitative | 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.
- DiT4SR — DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution (ICCV 2025) · better on 6 of 6 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
- EditBridge: Towards Faithful and Efficient Ultra-High-Resolution Image Editing (NeurIPS 2026 · similarity 0.88)
- ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance (AAAI 2025 · similarity 0.85)
- HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance (NeurIPS 2025 · similarity 0.85)
- From Scale to Speed: Adaptive Test-Time Scaling for Image Editing (CVPR 2026 · similarity 0.85)
- UltraEdit: Instruction-based Fine-Grained Image Editing at Scale (NeurIPS 2024 · similarity 0.84)
- VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling (NeurIPS 2026 · 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.
