LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image 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_ | 1866910897265442816 |
|---|---|
| author | Soni, Achint Soni, Meet Rambhatla, Sirisha |
| author_facet | Soni, Achint Soni, Meet Rambhatla, Sirisha |
| contents | Text-guided image editing aims to modify specific regions of an image according to natural language instructions while maintaining the general structure and the background fidelity. Existing methods utilize masks derived from cross-attention maps generated from diffusion models to identify the target regions for modification. However, since cross-attention mechanisms focus on semantic relevance, they struggle to maintain the image integrity. As a result, these methods often lack spatial consistency, leading to editing artifacts and distortions. In this work, we address these limitations and introduce LOCATEdit, which enhances cross-attention maps through a graph-based approach utilizing self-attention-derived patch relationships to maintain smooth, coherent attention across image regions, ensuring that alterations are limited to the designated items while retaining the surrounding structure. LOCATEdit consistently and substantially outperforms existing baselines on PIE-Bench, demonstrating its state-of-the-art performance and effectiveness on various editing tasks. Code can be found on https://github.com/LOCATEdit/LOCATEdit/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21541 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing Soni, Achint Soni, Meet Rambhatla, Sirisha Computer Vision and Pattern Recognition Artificial Intelligence Text-guided image editing aims to modify specific regions of an image according to natural language instructions while maintaining the general structure and the background fidelity. Existing methods utilize masks derived from cross-attention maps generated from diffusion models to identify the target regions for modification. However, since cross-attention mechanisms focus on semantic relevance, they struggle to maintain the image integrity. As a result, these methods often lack spatial consistency, leading to editing artifacts and distortions. In this work, we address these limitations and introduce LOCATEdit, which enhances cross-attention maps through a graph-based approach utilizing self-attention-derived patch relationships to maintain smooth, coherent attention across image regions, ensuring that alterations are limited to the designated items while retaining the surrounding structure. LOCATEdit consistently and substantially outperforms existing baselines on PIE-Bench, demonstrating its state-of-the-art performance and effectiveness on various editing tasks. Code can be found on https://github.com/LOCATEdit/LOCATEdit/ |
| title | LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.21541 |