Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908381116104704 |
|---|---|
| author | Zhao, Xiangyu Zhang, Peiyuan Tang, Kexian Zhu, Xiaorong Li, Hao Chai, Wenhao Zhang, Zicheng Xia, Renqiu Zhai, Guangtao Yan, Junchi Yang, Hua Yang, Xue Duan, Haodong |
| author_facet | Zhao, Xiangyu Zhang, Peiyuan Tang, Kexian Zhu, Xiaorong Li, Hao Chai, Wenhao Zhang, Zicheng Xia, Renqiu Zhai, Guangtao Yan, Junchi Yang, Hua Yang, Xue Duan, Haodong |
| contents | Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in following complex instructions, preserving appearance consistency, and supporting flexible input formats. To study this gap, we introduce RISEBench, the first benchmark for evaluating Reasoning-Informed viSual Editing (RISE). RISEBench focuses on four key reasoning categories: Temporal, Causal, Spatial, and Logical Reasoning. We curate high-quality test cases for each category and propose an robust evaluation framework that assesses Instruction Reasoning, Appearance Consistency, and Visual Plausibility with both human judges and the LMM-as-a-judge approach. We conducted experiments evaluating nine prominent visual editing models, comprising both open-source and proprietary models. The evaluation results demonstrate that current models face significant challenges in reasoning-based editing tasks. Even the most powerful model evaluated, GPT-4o-Image, achieves an accuracy of merely 28.8%. RISEBench effectively highlights the limitations of contemporary editing models, provides valuable insights, and indicates potential future directions for the field of reasoning-aware visual editing. Our code and data have been released at https://github.com/PhoenixZ810/RISEBench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02826 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing Zhao, Xiangyu Zhang, Peiyuan Tang, Kexian Zhu, Xiaorong Li, Hao Chai, Wenhao Zhang, Zicheng Xia, Renqiu Zhai, Guangtao Yan, Junchi Yang, Hua Yang, Xue Duan, Haodong Computer Vision and Pattern Recognition Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in following complex instructions, preserving appearance consistency, and supporting flexible input formats. To study this gap, we introduce RISEBench, the first benchmark for evaluating Reasoning-Informed viSual Editing (RISE). RISEBench focuses on four key reasoning categories: Temporal, Causal, Spatial, and Logical Reasoning. We curate high-quality test cases for each category and propose an robust evaluation framework that assesses Instruction Reasoning, Appearance Consistency, and Visual Plausibility with both human judges and the LMM-as-a-judge approach. We conducted experiments evaluating nine prominent visual editing models, comprising both open-source and proprietary models. The evaluation results demonstrate that current models face significant challenges in reasoning-based editing tasks. Even the most powerful model evaluated, GPT-4o-Image, achieves an accuracy of merely 28.8%. RISEBench effectively highlights the limitations of contemporary editing models, provides valuable insights, and indicates potential future directions for the field of reasoning-aware visual editing. Our code and data have been released at https://github.com/PhoenixZ810/RISEBench. |
| title | Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.02826 |