Monocular 3D Object Detection via Geometric Reasoning on Keypoints

Ivan Barabanau, Alexey Artemov, Evgeny Burnaev, Vyacheslav Murashkin

2020

Abstract

Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D detections. In this paper, we propose a novel keypoint-based approach for 3D object detection and localization from a single RGB image. We build our multi-branch model around 2D keypoint detection in images and complement it with a conceptually simple geometric reasoning method. Our network performs in an end-to-end manner, simultaneously and interdependently estimating 2D characteristics, such as 2D bounding boxes, keypoints, and orientation, along with full 3D pose in the scene. We fuse the outputs of distinct branches, applying a reprojection consistency loss during training. The experimental evaluation on the challenging KITTI dataset benchmark demonstrates that our network achieves state-of-the-art results among other monocular 3D detectors.

Paper Citation

in Harvard Style

Barabanau I., Artemov A., Burnaev E. and Murashkin V. (2020). Monocular 3D Object Detection via Geometric Reasoning on Keypoints. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 652-659. DOI: 10.5220/0009102506520659

in Bibtex Style

@conference{visapp20,
author={Ivan Barabanau and Alexey Artemov and Evgeny Burnaev and Vyacheslav Murashkin},
title={Monocular 3D Object Detection via Geometric Reasoning on Keypoints},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={652-659},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009102506520659},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - Monocular 3D Object Detection via Geometric Reasoning on Keypoints
SN - 978-989-758-402-2
AU - Barabanau I.
AU - Artemov A.
AU - Burnaev E.
AU - Murashkin V.
PY - 2020
SP - 652
EP - 659
DO - 10.5220/0009102506520659
PB - SciTePress