Virtual Try
Virtual try-on (VTON) technology aims to realistically simulate the appearance of clothing on individuals using digital images, enhancing online shopping experiences and reducing return rates. Current research heavily utilizes diffusion models, often coupled with techniques like Gaussian splatting and ControlNet, to achieve high-fidelity results, addressing challenges such as handling diverse poses, occlusions (especially from hands), and generating realistic textures and wrinkles. This field is significant for its potential to revolutionize online retail and fashion design by providing more accurate and engaging virtual previews of clothing items, accessories, and even hairstyles.
Papers
Tunnel Try-on: Excavating Spatial-temporal Tunnels for High-quality Virtual Try-on in Videos
Zhengze Xu, Mengting Chen, Zhao Wang, Linyu Xing, Zhonghua Zhai, Nong Sang, Jinsong Lan, Shuai Xiao, Changxin Gao
MV-VTON: Multi-View Virtual Try-On with Diffusion Models
Haoyu Wang, Zhilu Zhang, Donglin Di, Shiliang Zhang, Wangmeng Zuo
HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach
Maxim Nikolaev, Mikhail Kuznetsov, Dmitry Vetrov, Aibek Alanov
Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On
Xu Yang, Changxing Ding, Zhibin Hong, Junhao Huang, Jin Tao, Xiangmin Xu
TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On
Jiazheng Xing, Chao Xu, Yijie Qian, Yang Liu, Guang Dai, Baigui Sun, Yong Liu, Jingdong Wang