Qingnan Fan, Baoquan Chen, Leonidas Guibas, Hao Su, Qiang Zhou, Yuzhe Qin, He Wang, Yijia Weng, Yueqi Duan
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Figure 1. Our method tracks 9DoF category-level poses (3D rotation, 3D translation, and 3D size) of novel rigid objects as well as parts in articulated objects from live point cloud streams. We demonstrate: (a) our method can reliably track rigid object poses from the challenging NOCS-REAL275 dataset [29]; (b) our method can perfectly track articulated objects with big global and articulated motions from the SAPIEN datasets[34]; (c)(d) trained only on SAPIEN, our model can directly generalize to novel real laptops from BMVC dataset[18], and novel real drawers under robotic interaction. In all cases, our method significantly outperforms the previous state-of-thearts and baselines. Here we visualize the estimated 9DoF poses as 3D bounding boxes: green boxes indicate in tracking whereas red boxes indicate off tracking.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.03437")
get_code_for_paper("2104.03437")
have("2104.03437")
Connect an agent — have() is free.