Towards Generalized and Training-Free Text-Guided Semantic Manipulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916819117277184 |
|---|---|
| author | Hong, Yu Cai, Xiao Zeng, Pengpeng Zhang, Shuai Song, Jingkuan Gao, Lianli Shen, Heng Tao |
| author_facet | Hong, Yu Cai, Xiao Zeng, Pengpeng Zhang, Shuai Song, Jingkuan Gao, Lianli Shen, Heng Tao |
| contents | Text-guided semantic manipulation refers to semantically editing an image generated from a source prompt to match a target prompt, enabling the desired semantic changes (e.g., addition, removal, and style transfer) while preserving irrelevant contents. With the powerful generative capabilities of the diffusion model, the task has shown the potential to generate high-fidelity visual content. Nevertheless, existing methods either typically require time-consuming fine-tuning (inefficient), fail to accomplish multiple semantic manipulations (poorly extensible), and/or lack support for different modality tasks (limited generalizability). Upon further investigation, we find that the geometric properties of noises in the diffusion model are strongly correlated with the semantic changes. Motivated by this, we propose a novel $\textit{GTF}$ for text-guided semantic manipulation, which has the following attractive capabilities: 1) $\textbf{Generalized}$: our $\textit{GTF}$ supports multiple semantic manipulations (e.g., addition, removal, and style transfer) and can be seamlessly integrated into all diffusion-based methods (i.e., Plug-and-play) across different modalities (i.e., modality-agnostic); and 2) $\textbf{Training-free}$: $\textit{GTF}$ produces high-fidelity results via simply controlling the geometric relationship between noises without tuning or optimization. Our extensive experiments demonstrate the efficacy of our approach, highlighting its potential to advance the state-of-the-art in semantics manipulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17269 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Generalized and Training-Free Text-Guided Semantic Manipulation Hong, Yu Cai, Xiao Zeng, Pengpeng Zhang, Shuai Song, Jingkuan Gao, Lianli Shen, Heng Tao Computer Vision and Pattern Recognition Text-guided semantic manipulation refers to semantically editing an image generated from a source prompt to match a target prompt, enabling the desired semantic changes (e.g., addition, removal, and style transfer) while preserving irrelevant contents. With the powerful generative capabilities of the diffusion model, the task has shown the potential to generate high-fidelity visual content. Nevertheless, existing methods either typically require time-consuming fine-tuning (inefficient), fail to accomplish multiple semantic manipulations (poorly extensible), and/or lack support for different modality tasks (limited generalizability). Upon further investigation, we find that the geometric properties of noises in the diffusion model are strongly correlated with the semantic changes. Motivated by this, we propose a novel $\textit{GTF}$ for text-guided semantic manipulation, which has the following attractive capabilities: 1) $\textbf{Generalized}$: our $\textit{GTF}$ supports multiple semantic manipulations (e.g., addition, removal, and style transfer) and can be seamlessly integrated into all diffusion-based methods (i.e., Plug-and-play) across different modalities (i.e., modality-agnostic); and 2) $\textbf{Training-free}$: $\textit{GTF}$ produces high-fidelity results via simply controlling the geometric relationship between noises without tuning or optimization. Our extensive experiments demonstrate the efficacy of our approach, highlighting its potential to advance the state-of-the-art in semantics manipulation. |
| title | Towards Generalized and Training-Free Text-Guided Semantic Manipulation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.17269 |