Research map / Image generation / Autoregressive and latent generation
VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset
Zhizhou Chen, Shanyan Guan, Zhanxin Gao, En Ci, Yanhao Ge, Wei Li, Zhenyu Zhang, Jian Yang, Ying Tai
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 high-frequency-aware post-adaptation (attention and RoPE rescaling plus FFS) (ablation) | Kontext-dev · VINS-4KEval | pFID: 15.01 -> 9.15 | Improved |
| add post-adaptation (ablation) | Kontext-dev · VINS-4KEval | VIEScore: 5.15 -> 7.44 | Improved |
| add data curation to the UHR dataset (ablation) | Kontext post-adaptation · VINS-4KEval | ImageJudge: 4.33 -> 4.47 | Improved |
| add data curation to the UHR dataset (ablation) | Kontext post-adaptation · VINS-4KEval | pFID: 13.17 -> 9.15 | Hurt |
| add synthetic upscaled data to real frames (ablation) | Kontext post-adaptation · VINS-4KEval | pFID: 8.96 -> 9.15 | Hurt |
| add synthetic upscaled data to real frames (ablation) | Kontext post-adaptation · VINS-4KEval | ImageJudge / VIEScore: 4.39 / 7.30 -> 4.47 / 7.44 | Improved |
| apply post-adaptation to Kontext-dev | Kontext-dev · VINS-4KEval | pFID: 12.66 -> 9.15 | Improved |
| apply post-adaptation to Kontext-dev | Kontext-dev · VINS-4KEval | ImageJudge: 4.22 -> 4.23 | No clear effect |
| apply post-adaptation to QwenImage-Edit instead of SR | QwenImage-Edit-2511 · VINS-4KEval | pFID: 18.33 -> 11.38 | Improved |
| apply post-adaptation to QwenImage-Edit instead of SR | QwenImage-Edit-2511 · VINS-4KEval | ImageJudge: 4.67 -> 4.69 | No clear effect |
| use frequency-focused loss L_freq instead of L_SWFR (ablation) | Kontext post-adaptation · VINS-4KEval | pFID: 9.64 -> 9.15 | Improved |
| add L_freq to flow-matching loss (ablation) | Kontext post-adaptation · VINS-4KEval | pFID: 9.25 -> 9.15 | 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.
- AnyEdit — AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea (CVPR 2025) · better on 2 of 2 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
- UltraEdit: Instruction-based Fine-Grained Image Editing at Scale (NeurIPS 2024 · similarity 0.89)
- EditBridge: Towards Faithful and Efficient Ultra-High-Resolution Image Editing (NeurIPS 2026 · similarity 0.89)
- UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset (NeurIPS 2025 · similarity 0.89)
- From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective (CVPR 2025 · similarity 0.87)
- ImgEdit: A Unified Image Editing Dataset and Benchmark (NeurIPS 2025 · similarity 0.86)
- HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing (ICLR 2025 · 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.
