UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911298539749376 |
|---|---|
| author | Bai, Chengyu Chen, Jintao Bai, Xiang Chen, Yilong She, Qi Lu, Ming Zhang, Shanghang |
| author_facet | Bai, Chengyu Chen, Jintao Bai, Xiang Chen, Yilong She, Qi Lu, Ming Zhang, Shanghang |
| contents | While Unified Vision-Language Models promise to synergistically combine the high-level semantic understanding of vision-language models with the generative fidelity of diffusion models, current editing methodologies remain fundamentally decoupled and open loop performing static, pre-defined transformations without dynamic feedback between semantic interpretation and visual generation. A central limitation stems from the representation gap: understanding typically leverages high-level, language aligned encoders, whereas generation relies on low level, pixel-space autoencoders, resulting in misaligned feature spaces. To bridge this gap, Recent advances such as Representation Autoencoders and BLIP3-o advocate performing diffusion-based modeling directly in high level features from pretrained semantic encoders. We find editing in the semantic latent space modifies conceptual representations rather than pixels, ensuring intermediates that are both semantically coherent and visually plausible. Building on this insight, We propose UniEdit-I, the first training-free, closed-loop image editing framework that operates entirely within the semantic latent space of a unified VLM by introducing an Understanding-Editing-Verifying (UEV) loop, By transforming the VLM from a posthoc evaluator into an in-process conductor, UniEdit-I establishes the first semantics-driven, self-correcting closed-loop image editing pipeline. Evaluated on GEdit-Bench, UniEdit-I achieves state of the art performance without any fine tuning or architectural modifications, and even surpasses several largescale pretrained editors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03142 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying Bai, Chengyu Chen, Jintao Bai, Xiang Chen, Yilong She, Qi Lu, Ming Zhang, Shanghang Computer Vision and Pattern Recognition While Unified Vision-Language Models promise to synergistically combine the high-level semantic understanding of vision-language models with the generative fidelity of diffusion models, current editing methodologies remain fundamentally decoupled and open loop performing static, pre-defined transformations without dynamic feedback between semantic interpretation and visual generation. A central limitation stems from the representation gap: understanding typically leverages high-level, language aligned encoders, whereas generation relies on low level, pixel-space autoencoders, resulting in misaligned feature spaces. To bridge this gap, Recent advances such as Representation Autoencoders and BLIP3-o advocate performing diffusion-based modeling directly in high level features from pretrained semantic encoders. We find editing in the semantic latent space modifies conceptual representations rather than pixels, ensuring intermediates that are both semantically coherent and visually plausible. Building on this insight, We propose UniEdit-I, the first training-free, closed-loop image editing framework that operates entirely within the semantic latent space of a unified VLM by introducing an Understanding-Editing-Verifying (UEV) loop, By transforming the VLM from a posthoc evaluator into an in-process conductor, UniEdit-I establishes the first semantics-driven, self-correcting closed-loop image editing pipeline. Evaluated on GEdit-Bench, UniEdit-I achieves state of the art performance without any fine tuning or architectural modifications, and even surpasses several largescale pretrained editors. |
| title | UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.03142 |