I. Introduction
Virtual try-on is a promising topic for commercial applications in computer vision. The image-based virtual try-on has no requirements for professional 3 d modeling of the person [1], [2] and garment [3]. It still preset a photo-realistic wearing effect only conditioned on the person and garment image. However, as the variability of person and garment increases, the content inference and garment warping employed in previous studies have encountered challenges when faced with difficult try-on scenarios. In this paper, we propose a progressive inference paradigm of virtual try-on and employ advanced strategies of garment try-on and skin inpainting to enhance the try-on realism even in the presence of distinct garment categories or complex poses.