English

Simultaneous Multiple Object Detection and Pose Estimation using 3D Model Infusion with Monocular Vision

Computer Vision and Pattern Recognition 2024-12-24 v3

Abstract

Multiple object detection and pose estimation are vital computer vision tasks. The latter relates to the former as a downstream problem in applications such as robotics and autonomous driving. However, due to the high complexity of both tasks, existing methods generally treat them independently, which is sub-optimal. We propose simultaneous neural modeling of both using monocular vision and 3D model infusion. Our Simultaneous Multiple Object detection and Pose Estimation network (SMOPE-Net) is an end-to-end trainable multitasking network with a composite loss that also provides the advantages of anchor-free detections for efficient downstream pose estimation. To enable the annotation of training data for our learning objective, we develop a Twin-Space object labeling method and demonstrate its correctness analytically and empirically. Using the labeling method, we provide the KITTI-6DoF dataset with 7.5\sim7.5K annotated frames. Extensive experiments on KITTI-6DoF and the popular LineMod datasets show a consistent performance gain with SMOPE-Net over existing pose estimation methods. Here are links to our proposed SMOPE-Net, KITTI-6DoF dataset, and LabelImg3D labeling tool.

Keywords

Cite

@article{arxiv.2211.11188,
  title  = {Simultaneous Multiple Object Detection and Pose Estimation using 3D Model Infusion with Monocular Vision},
  author = {Congliang Li and Shijie Sun and Xiangyu Song and Huansheng Song and Naveed Akhtar and Ajmal Saeed Mian},
  journal= {arXiv preprint arXiv:2211.11188},
  year   = {2024}
}

Comments

Thesis needs further optimization

R2 v1 2026-06-28T06:20:09.934Z