Saved in:
Bibliographic Details
Main Authors: Lin, Yongliang, Su, Yongzhi, Inuganti, Sandeep, Di, Yan, Ajilforoushan, Naeem, Yang, Hanqing, Zhang, Yu, Rambach, Jason
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.10557
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917668671455232
author Lin, Yongliang
Su, Yongzhi
Inuganti, Sandeep
Di, Yan
Ajilforoushan, Naeem
Yang, Hanqing
Zhang, Yu
Rambach, Jason
author_facet Lin, Yongliang
Su, Yongzhi
Inuganti, Sandeep
Di, Yan
Ajilforoushan, Naeem
Yang, Hanqing
Zhang, Yu
Rambach, Jason
contents Estimating the 6D pose of an object from a single RGB image is a critical task that becomes additionally challenging when dealing with symmetric objects. Recent approaches typically establish one-to-one correspondences between image pixels and 3D object surface vertices. However, the utilization of one-to-one correspondences introduces ambiguity for symmetric objects. To address this, we propose SymCode, a symmetry-aware surface encoding that encodes the object surface vertices based on one-to-many correspondences, eliminating the problem of one-to-one correspondence ambiguity. We also introduce SymNet, a fast end-to-end network that directly regresses the 6D pose parameters without solving a PnP problem. We demonstrate faster runtime and comparable accuracy achieved by our method on the T-LESS and IC-BIN benchmarks of mostly symmetric objects. Our source code will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10557
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Resolving Symmetry Ambiguity in Correspondence-based Methods for Instance-level Object Pose Estimation
Lin, Yongliang
Su, Yongzhi
Inuganti, Sandeep
Di, Yan
Ajilforoushan, Naeem
Yang, Hanqing
Zhang, Yu
Rambach, Jason
Computer Vision and Pattern Recognition
Estimating the 6D pose of an object from a single RGB image is a critical task that becomes additionally challenging when dealing with symmetric objects. Recent approaches typically establish one-to-one correspondences between image pixels and 3D object surface vertices. However, the utilization of one-to-one correspondences introduces ambiguity for symmetric objects. To address this, we propose SymCode, a symmetry-aware surface encoding that encodes the object surface vertices based on one-to-many correspondences, eliminating the problem of one-to-one correspondence ambiguity. We also introduce SymNet, a fast end-to-end network that directly regresses the 6D pose parameters without solving a PnP problem. We demonstrate faster runtime and comparable accuracy achieved by our method on the T-LESS and IC-BIN benchmarks of mostly symmetric objects. Our source code will be released upon acceptance.
title Resolving Symmetry Ambiguity in Correspondence-based Methods for Instance-level Object Pose Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.10557