Views
No views yet
ASUKA solves two issues existed in current diffusion and rectified flow inpainting models: Unwanted object insertion, where randomly elements that are not aligned with the unmasked region are generated; Color-inconsistency, the color shift of the generated masked region, causing smear-like traces. ASUKA proposes a post-training procedure for these models, significantly mitigates object hallucination and improves color consistency of inpainted results.
1@inproceedings{wang2025towards,
2 title={Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency.},
3 author={Wang, Yikai and Cao, Chenjie and Yu, Junqiu and Fan, Ke and Xue, Xiangyang and Fu, Yanwei},
4 booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
5 year={2025}
6}