@article{catv2tontamingdiffusiontransformersfor,
  title = {CatV2TON: Taming Diffusion Transformers for Vision-Based Virtual Try-On with Temporal Concatenation},
  author = {Zheng Chong and Wenqing Zhang and Shiyue Zhang and Jun Zheng and Xiao Dong and Haoxiang Li and Yiling Wu and Dongmei Jiang and Xiaodan Liang},
  year = {2025},
  eprint = {2501.11325},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.11325v1},
}