Favor: Full-Body AR-driven Virtual Object Rearrangement Guided by Instruction Text

OakBase: Object Affordance Knowledge (Oak) base, including objects' part-level segmentation and attributes.
OakInk-Image: a video dataset with 3D hand-object pose and shape annotations.
OakInk-Shape: a 3D grasping pose dataset with hand and object mesh models.

Kailin Li^1*, Lixin Yang^1*, Zenan Lin³, Jian Xu², Xinyu Zhan¹, Yifei Zhao¹, Pengxiang Zhu¹, Wenxiong Kang³, Kejian Wu², Cewu Lu^1✉

¹Shanghai Jiao Tong University, ²XREAL ³South China University of Technology

* Equal contribution ✉ Corresponding author

AAAI 2024

Paper Code(Coming Soon) Dataset(Coming Soon)

Update

Dec,09,2023: FAVOR got accepted by AAAI 2024.

BibTeX


@article{Li_Yang_Lin_Xu_Zhan_Zhao_Zhu_Kang_Wu_Lu_2024,
  title={FAVOR: Full-Body AR-Driven Virtual Object Rearrangement Guided by Instruction Text},
  volume={38},
  number={4},
  journal={Proceedings of the AAAI Conference on Artificial Intelligence},
  author={Li, Kailin and Yang, Lixin and Lin, Zenan and Xu, Jian and Zhan, Xinyu and Zhao, Yifei and Zhu, Pengxiang and Kang, Wenxiong and Wu, Kejian and Lu, Cewu},
  year={2024},
  pages={3136-3144}
}