{"ID":2859886,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04822","arxiv_id":"2510.04822","title":"AvatarVTON: 4D Virtual Try-On for Animatable Avatars","abstract":"We propose AvatarVTON, the first 4D virtual try-on framework that generates realistic try-on results from a single in-shop garment image, enabling free pose control, novel-view rendering, and diverse garment choices. Unlike existing methods, AvatarVTON supports dynamic garment interactions under single-view supervision, without relying on multi-view garment captures or physics priors. The framework consists of two key modules: (1) a Reciprocal Flow Rectifier, a prior-free optical-flow correction strategy that stabilizes avatar fitting and ensures temporal coherence; and (2) a Non-Linear Deformer, which decomposes Gaussian maps into view-pose-invariant and view-pose-specific components, enabling adaptive, non-linear garment deformations. To establish a benchmark for 4D virtual try-on, we extend existing baselines with unified modules for fair qualitative and quantitative comparisons. Extensive experiments show that AvatarVTON achieves high fidelity, diversity, and dynamic garment realism, making it well-suited for AR/VR, gaming, and digital-human applications.","short_abstract":"We propose AvatarVTON, the first 4D virtual try-on framework that generates realistic try-on results from a single in-shop garment image, enabling free pose control, novel-view rendering, and diverse garment choices. Unlike existing methods, AvatarVTON supports dynamic garment interactions under single-view supervision...","url_abs":"https://arxiv.org/abs/2510.04822","url_pdf":"https://arxiv.org/pdf/2510.04822v1","authors":"[\"Zicheng Jiang\",\"Jixin Gao\",\"Shengfeng He\",\"Xinzhe Li\",\"Yulong Zheng\",\"Zhaotong Yang\",\"Junyu Dong\",\"Yong Du\"]","published":"2025-10-06T14:06:34Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}