Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.16702 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910168026972160 |
|---|---|
| author | Liu, Chen Wu, Haitao Wang, Kafeng Huang, Weiran |
| author_facet | Liu, Chen Wu, Haitao Wang, Kafeng Huang, Weiran |
| contents | Personalized animal image generation is challenging due to rich appearance cues and large morphological variability. Existing approaches often exhibit feature misalignment across domains, which leads to identity drift. We present AnimalBooth, a framework that strengthens identity preservation with an Animal Net and an adaptive attention module, mitigating cross domain alignment errors. We further introduce a frequency controlled feature integration module that applies Discrete Cosine Transform filtering in the latent space to guide the diffusion process, enabling a coarse to fine progression from global structure to detailed texture. To advance research in this area, we curate AnimalBench, a high resolution dataset for animal personalization. Extensive experiments show that AnimalBooth consistently outperforms strong baselines on multiple benchmarks and improves both identity fidelity and perceptual quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16702 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Animalbooth: multimodal feature enhancement for animal subject personalization Liu, Chen Wu, Haitao Wang, Kafeng Huang, Weiran Computer Vision and Pattern Recognition Personalized animal image generation is challenging due to rich appearance cues and large morphological variability. Existing approaches often exhibit feature misalignment across domains, which leads to identity drift. We present AnimalBooth, a framework that strengthens identity preservation with an Animal Net and an adaptive attention module, mitigating cross domain alignment errors. We further introduce a frequency controlled feature integration module that applies Discrete Cosine Transform filtering in the latent space to guide the diffusion process, enabling a coarse to fine progression from global structure to detailed texture. To advance research in this area, we curate AnimalBench, a high resolution dataset for animal personalization. Extensive experiments show that AnimalBooth consistently outperforms strong baselines on multiple benchmarks and improves both identity fidelity and perceptual quality. |
| title | Animalbooth: multimodal feature enhancement for animal subject personalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.16702 |