FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915071850971136 |
|---|---|
| author | Nguyen, Trong-Tung Nguyen, Duc-Anh Tran, Anh Pham, Cuong |
| author_facet | Nguyen, Trong-Tung Nguyen, Duc-Anh Tran, Anh Pham, Cuong |
| contents | Our work addresses limitations seen in previous approaches for object-centric editing problems, such as unrealistic results due to shape discrepancies and limited control in object replacement or insertion. To this end, we introduce FlexEdit, a flexible and controllable editing framework for objects where we iteratively adjust latents at each denoising step using our FlexEdit block. Initially, we optimize latents at test time to align with specified object constraints. Then, our framework employs an adaptive mask, automatically extracted during denoising, to protect the background while seamlessly blending new content into the target image. We demonstrate the versatility of FlexEdit in various object editing tasks and curate an evaluation test suite with samples from both real and synthetic images, along with novel evaluation metrics designed for object-centric editing. We conduct extensive experiments on different editing scenarios, demonstrating the superiority of our editing framework over recent advanced text-guided image editing methods. Our project page is published at https://flex-edit.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_18605 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing Nguyen, Trong-Tung Nguyen, Duc-Anh Tran, Anh Pham, Cuong Computer Vision and Pattern Recognition Our work addresses limitations seen in previous approaches for object-centric editing problems, such as unrealistic results due to shape discrepancies and limited control in object replacement or insertion. To this end, we introduce FlexEdit, a flexible and controllable editing framework for objects where we iteratively adjust latents at each denoising step using our FlexEdit block. Initially, we optimize latents at test time to align with specified object constraints. Then, our framework employs an adaptive mask, automatically extracted during denoising, to protect the background while seamlessly blending new content into the target image. We demonstrate the versatility of FlexEdit in various object editing tasks and curate an evaluation test suite with samples from both real and synthetic images, along with novel evaluation metrics designed for object-centric editing. We conduct extensive experiments on different editing scenarios, demonstrating the superiority of our editing framework over recent advanced text-guided image editing methods. Our project page is published at https://flex-edit.github.io/. |
| title | FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.18605 |