CAMILA: Context-Aware Masking for Image Editing with Language Alignment
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915530346070016 |
|---|---|
| author | Kim, Hyunseung Choi, Chiho Malla, Srikanth Padmanabhan, Sai Prahladh Bagchi, Saurabh Choi, Joon Hee |
| author_facet | Kim, Hyunseung Choi, Chiho Malla, Srikanth Padmanabhan, Sai Prahladh Bagchi, Saurabh Choi, Joon Hee |
| contents | Text-guided image editing has been allowing users to transform and synthesize images through natural language instructions, offering considerable flexibility. However, most existing image editing models naively attempt to follow all user instructions, even if those instructions are inherently infeasible or contradictory, often resulting in nonsensical output. To address these challenges, we propose a context-aware method for image editing named as CAMILA (Context-Aware Masking for Image Editing with Language Alignment). CAMILA is designed to validate the contextual coherence between instructions and the image, ensuring that only relevant edits are applied to the designated regions while ignoring non-executable instructions. For comprehensive evaluation of this new method, we constructed datasets for both single- and multi-instruction image editing, incorporating the presence of infeasible requests. Our method achieves better performance and higher semantic alignment than state-of-the-art models, demonstrating its effectiveness in handling complex instruction challenges while preserving image integrity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19731 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CAMILA: Context-Aware Masking for Image Editing with Language Alignment Kim, Hyunseung Choi, Chiho Malla, Srikanth Padmanabhan, Sai Prahladh Bagchi, Saurabh Choi, Joon Hee Computer Vision and Pattern Recognition Text-guided image editing has been allowing users to transform and synthesize images through natural language instructions, offering considerable flexibility. However, most existing image editing models naively attempt to follow all user instructions, even if those instructions are inherently infeasible or contradictory, often resulting in nonsensical output. To address these challenges, we propose a context-aware method for image editing named as CAMILA (Context-Aware Masking for Image Editing with Language Alignment). CAMILA is designed to validate the contextual coherence between instructions and the image, ensuring that only relevant edits are applied to the designated regions while ignoring non-executable instructions. For comprehensive evaluation of this new method, we constructed datasets for both single- and multi-instruction image editing, incorporating the presence of infeasible requests. Our method achieves better performance and higher semantic alignment than state-of-the-art models, demonstrating its effectiveness in handling complex instruction challenges while preserving image integrity. |
| title | CAMILA: Context-Aware Masking for Image Editing with Language Alignment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.19731 |