Saved in:
Bibliographic Details
Main Authors: Zhao, Jianyu, Quan, Wei, Matuszewski, Bogdan J.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.09010
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909345879425024
author Zhao, Jianyu
Quan, Wei
Matuszewski, Bogdan J.
author_facet Zhao, Jianyu
Quan, Wei
Matuszewski, Bogdan J.
contents Estimating rigid objects' poses is one of the fundamental problems in computer vision, with a range of applications across automation and augmented reality. Most existing approaches adopt one network per object class strategy, depend heavily on objects' 3D models, depth data, and employ a time-consuming iterative refinement, which could be impractical for some applications. This paper presents a novel approach, CVAM-Pose, for multi-object monocular pose estimation that addresses these limitations. The CVAM-Pose method employs a label-embedded conditional variational autoencoder network, to implicitly abstract regularised representations of multiple objects in a single low-dimensional latent space. This autoencoding process uses only images captured by a projective camera and is robust to objects' occlusion and scene clutter. The classes of objects are one-hot encoded and embedded throughout the network. The proposed label-embedded pose regression strategy interprets the learnt latent space representations utilising continuous pose representations. Ablation tests and systematic evaluations demonstrate the scalability and efficiency of the CVAM-Pose method for multi-object scenarios. The proposed CVAM-Pose outperforms competing latent space approaches. For example, it is respectively 25% and 20% better than AAE and Multi-Path methods, when evaluated using the $\mathrm{AR_{VSD}}$ metric on the Linemod-Occluded dataset. It also achieves results somewhat comparable to methods reliant on 3D models reported in BOP challenges. Code available: https://github.com/JZhao12/CVAM-Pose
format Preprint
id arxiv_https___arxiv_org_abs_2410_09010
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CVAM-Pose: Conditional Variational Autoencoder for Multi-Object Monocular Pose Estimation
Zhao, Jianyu
Quan, Wei
Matuszewski, Bogdan J.
Computer Vision and Pattern Recognition
Estimating rigid objects' poses is one of the fundamental problems in computer vision, with a range of applications across automation and augmented reality. Most existing approaches adopt one network per object class strategy, depend heavily on objects' 3D models, depth data, and employ a time-consuming iterative refinement, which could be impractical for some applications. This paper presents a novel approach, CVAM-Pose, for multi-object monocular pose estimation that addresses these limitations. The CVAM-Pose method employs a label-embedded conditional variational autoencoder network, to implicitly abstract regularised representations of multiple objects in a single low-dimensional latent space. This autoencoding process uses only images captured by a projective camera and is robust to objects' occlusion and scene clutter. The classes of objects are one-hot encoded and embedded throughout the network. The proposed label-embedded pose regression strategy interprets the learnt latent space representations utilising continuous pose representations. Ablation tests and systematic evaluations demonstrate the scalability and efficiency of the CVAM-Pose method for multi-object scenarios. The proposed CVAM-Pose outperforms competing latent space approaches. For example, it is respectively 25% and 20% better than AAE and Multi-Path methods, when evaluated using the $\mathrm{AR_{VSD}}$ metric on the Linemod-Occluded dataset. It also achieves results somewhat comparable to methods reliant on 3D models reported in BOP challenges. Code available: https://github.com/JZhao12/CVAM-Pose
title CVAM-Pose: Conditional Variational Autoencoder for Multi-Object Monocular Pose Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.09010