English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this work, we tackle the problem of category-level online pose tracking ofobjects from point cloud sequences. For the first time, we propose a unifiedframework that can handle 9DoF pose tracking for novel rigid object instancesas well as per-part pose tracking for articulated objects from knowncategories. Here the 9DoF pose, comprising 6D pose and 3D size, is equivalentto a 3D amodal bounding box representation with free 6D pose. Given the depthpoint cloud at the current frame and the estimated pose from the last frame,our novel end-to-end pipeline learns to accurately update the pose. Ourpipeline is composed of three modules: 1) a pose canonicalization module thatnormalizes the pose of the input depth point cloud; 2) RotationNet, a modulethat directly regresses small interframe delta rotations; and 3) CoordinateNet,a module that predicts the normalized coordinates and segmentation, enablinganalytical computation of the 3D size and translation. Leveraging the smallpose regime in the pose-canonicalized point clouds, our method integrates thebest of both worlds by combining dense coordinate prediction and directrotation regression, thus yielding an end-to-end differentiable pipelineoptimized for 9DoF pose accuracy (without using non-differentiable RANSAC). Ourextensive experiments demonstrate that our method achieves new state-of-the-artperformance on category-level rigid object pose (NOCS-REAL275) and articulatedobject pose benchmarks (SAPIEN, BMVC) at the fastest FPS ~12.

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