Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909677706543104 |
|---|---|
| author | Yeh, Chun-Hsiao Wang, Yilin Zhao, Nanxuan Zhang, Richard Li, Yuheng Ma, Yi Singh, Krishna Kumar |
| author_facet | Yeh, Chun-Hsiao Wang, Yilin Zhao, Nanxuan Zhang, Richard Li, Yuheng Ma, Yi Singh, Krishna Kumar |
| contents | Recent diffusion-based image editing methods have significantly advanced text-guided tasks but often struggle to interpret complex, indirect instructions. Moreover, current models frequently suffer from poor identity preservation, unintended edits, or rely heavily on manual masks. To address these challenges, we introduce X-Planner, a Multimodal Large Language Model (MLLM)-based planning system that effectively bridges user intent with editing model capabilities. X-Planner employs chain-of-thought reasoning to systematically decompose complex instructions into simpler, clear sub-instructions. For each sub-instruction, X-Planner automatically generates precise edit types and segmentation masks, eliminating manual intervention and ensuring localized, identity-preserving edits. Additionally, we propose a novel automated pipeline for generating large-scale data to train X-Planner which achieves state-of-the-art results on both existing benchmarks and our newly introduced complex editing benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05259 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing Yeh, Chun-Hsiao Wang, Yilin Zhao, Nanxuan Zhang, Richard Li, Yuheng Ma, Yi Singh, Krishna Kumar Computer Vision and Pattern Recognition Recent diffusion-based image editing methods have significantly advanced text-guided tasks but often struggle to interpret complex, indirect instructions. Moreover, current models frequently suffer from poor identity preservation, unintended edits, or rely heavily on manual masks. To address these challenges, we introduce X-Planner, a Multimodal Large Language Model (MLLM)-based planning system that effectively bridges user intent with editing model capabilities. X-Planner employs chain-of-thought reasoning to systematically decompose complex instructions into simpler, clear sub-instructions. For each sub-instruction, X-Planner automatically generates precise edit types and segmentation masks, eliminating manual intervention and ensuring localized, identity-preserving edits. Additionally, we propose a novel automated pipeline for generating large-scale data to train X-Planner which achieves state-of-the-art results on both existing benchmarks and our newly introduced complex editing benchmark. |
| title | Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.05259 |