@article{m2pimprovingvisualfoundationmodelswithma,
  title = {M2P: Improving Visual Foundation Models with Mask-to-Point Weakly-Supervised Learning for Dense Point Tracking},
  author = {Qiangqiang Wu and Tianyu Yang and Bo Fang and Jia Wan and Matias Di Martino and Guillermo Sapiro and Antoni B. Chan},
  year = {2026},
  eprint = {2603.17813},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.17813},
}