HarmonPaint: Harmonized Training-Free Diffusion Inpainting
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908461170688000 |
|---|---|
| author | Li, Ying Li, Xinzhe Du, Yong Xu, Yangyang Dong, Junyu He, Shengfeng |
| author_facet | Li, Ying Li, Xinzhe Du, Yong Xu, Yangyang Dong, Junyu He, Shengfeng |
| contents | Existing inpainting methods often require extensive retraining or fine-tuning to integrate new content seamlessly, yet they struggle to maintain coherence in both structure and style between inpainted regions and the surrounding background. Motivated by these limitations, we introduce HarmonPaint, a training-free inpainting framework that seamlessly integrates with the attention mechanisms of diffusion models to achieve high-quality, harmonized image inpainting without any form of training. By leveraging masking strategies within self-attention, HarmonPaint ensures structural fidelity without model retraining or fine-tuning. Additionally, we exploit intrinsic diffusion model properties to transfer style information from unmasked to masked regions, achieving a harmonious integration of styles. Extensive experiments demonstrate the effectiveness of HarmonPaint across diverse scenes and styles, validating its versatility and performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16732 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HarmonPaint: Harmonized Training-Free Diffusion Inpainting Li, Ying Li, Xinzhe Du, Yong Xu, Yangyang Dong, Junyu He, Shengfeng Computer Vision and Pattern Recognition Existing inpainting methods often require extensive retraining or fine-tuning to integrate new content seamlessly, yet they struggle to maintain coherence in both structure and style between inpainted regions and the surrounding background. Motivated by these limitations, we introduce HarmonPaint, a training-free inpainting framework that seamlessly integrates with the attention mechanisms of diffusion models to achieve high-quality, harmonized image inpainting without any form of training. By leveraging masking strategies within self-attention, HarmonPaint ensures structural fidelity without model retraining or fine-tuning. Additionally, we exploit intrinsic diffusion model properties to transfer style information from unmasked to masked regions, achieving a harmonious integration of styles. Extensive experiments demonstrate the effectiveness of HarmonPaint across diverse scenes and styles, validating its versatility and performance. |
| title | HarmonPaint: Harmonized Training-Free Diffusion Inpainting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.16732 |