SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations

03/18/2023
by   Boyan Wan, et al.
0

Most learning-based approaches to category-level 6D pose estimation are design around normalized object coordinate space (NOCS). While being successful, NOCS-based methods become inaccurate and less robust when handling objects of a category containing significant intra-category shape variations. This is because the object coordinates induced by global and rigid alignment of objects are semantically incoherent, making the coordinate regression hard to learn and generalize. We propose Semantically-aware Object Coordinate Space (SOCS) built by warping-and-aligning the objects guided by a sparse set of keypoints with semantically meaningful correspondence. SOCS is semantically coherent: Any point on the surface of a object can be mapped to a semantically meaningful location in SOCS, allowing for accurate pose and size estimation under large shape variations. To learn effective coordinate regression to SOCS, we propose a novel multi-scale coordinate-based attention network. Evaluations demonstrate that our method is easy to train, well-generalizing for large intra-category shape variations and robust to inter-object occlusions.

READ FULL TEXT

page 1

page 3

page 6

page 7

page 8

research
09/01/2021

Category-Level Metric Scale Object Shape and Pose Estimation

Advances in deep learning recognition have led to accurate object detect...
research
03/15/2022

GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting

While 6D object pose estimation has recently made a huge leap forward, m...
research
12/26/2019

Category-Level Articulated Object Pose Estimation

This paper addresses the task of category-level pose estimation for arti...
research
08/01/2018

Category-level 6D Object Pose Recovery in Depth Images

Intra-class variations, distribution shifts among source and target doma...
research
11/18/2022

A mixed-reality dataset for category-level 6D pose and size estimation of hand-occluded containers

Estimating the 6D pose and size of household containers is challenging d...
research
08/13/2022

SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimation

Category-level pose estimation is a challenging problem due to intra-cla...
research
06/07/2023

Learning Probabilistic Coordinate Fields for Robust Correspondences

We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-i...

Please sign up or login with your details

Forgot password? Click here to reset