Specify and Edit: Overcoming Ambiguity in Text-Based Image Editing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929440844414976 |
|---|---|
| author | Iakovleva, Ekaterina Pizzati, Fabio Torr, Philip Lathuilière, Stéphane |
| author_facet | Iakovleva, Ekaterina Pizzati, Fabio Torr, Philip Lathuilière, Stéphane |
| contents | Text-based editing diffusion models exhibit limited performance when the user's input instruction is ambiguous. To solve this problem, we propose $\textit{Specify ANd Edit}$ (SANE), a zero-shot inference pipeline for diffusion-based editing systems. We use a large language model (LLM) to decompose the input instruction into specific instructions, i.e. well-defined interventions to apply to the input image to satisfy the user's request. We benefit from the LLM-derived instructions along the original one, thanks to a novel denoising guidance strategy specifically designed for the task. Our experiments with three baselines and on two datasets demonstrate the benefits of SANE in all setups. Moreover, our pipeline improves the interpretability of editing models, and boosts the output diversity. We also demonstrate that our approach can be applied to any edit, whether ambiguous or not. Our code is public at https://github.com/fabvio/SANE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20232 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Specify and Edit: Overcoming Ambiguity in Text-Based Image Editing Iakovleva, Ekaterina Pizzati, Fabio Torr, Philip Lathuilière, Stéphane Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Text-based editing diffusion models exhibit limited performance when the user's input instruction is ambiguous. To solve this problem, we propose $\textit{Specify ANd Edit}$ (SANE), a zero-shot inference pipeline for diffusion-based editing systems. We use a large language model (LLM) to decompose the input instruction into specific instructions, i.e. well-defined interventions to apply to the input image to satisfy the user's request. We benefit from the LLM-derived instructions along the original one, thanks to a novel denoising guidance strategy specifically designed for the task. Our experiments with three baselines and on two datasets demonstrate the benefits of SANE in all setups. Moreover, our pipeline improves the interpretability of editing models, and boosts the output diversity. We also demonstrate that our approach can be applied to any edit, whether ambiguous or not. Our code is public at https://github.com/fabvio/SANE. |
| title | Specify and Edit: Overcoming Ambiguity in Text-Based Image Editing |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2407.20232 |