Inpainting-Driven Mask Optimization for Object Removal

arXiv:2403.15849v1 Announce Type: new
Abstract: This paper proposes a mask optimization method for improving the quality of object removal using image inpainting. While many inpainting methods are trained with a set of random masks, a target for inpainting may be an object, such as a person, in many realistic scenarios. This domain gap between masks in training and inference images increases the difficulty of the inpainting task. In our method, this domain gap is resolved by training the inpainting network …

abstract arxiv cs.cv domain gap image improving inpainting masks object optimization paper person quality random set type