SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.03437 · ICCV · 2021

CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds

Qingnan Fan, Baoquan Chen, Leonidas Guibas, Hao Su, Qiang Zhou, Yuzhe Qin, He Wang, Yijia Weng, Yueqi Duan

arXiv · PDF · Open in the Atlas

Code that ran

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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

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.