LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing
This work improves localized image editing for users needing precise modifications, but it is incremental as it builds on existing cross-attention mechanisms.
The paper tackles the problem of text-guided image editing by addressing spatial inconsistencies and artifacts in existing methods, introducing LOCATEdit which uses a graph-based approach to enhance cross-attention maps, resulting in state-of-the-art performance on PIE-Bench.
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/