Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images

arXiv:2311.16094v2 Announce Type: replace
Abstract: Most existing methods for virtual try-on focus on studio person images with a limited range of poses and clean backgrounds. They can achieve plausible results for this studio try-on setting by learning to warp a garment image to fit a person's body from paired training data, i.e., garment images paired with images of people wearing the same garment. Such data is often collected from commercial websites, where each garment is demonstrated both by itself and …

abstract arxiv cs.cv cs.gr focus image images person results street studio training type virtual virtual try-on