SparseDet: Towards End-to-End 3D Object Detection

Jianhong Han, Zhaoyi Wan, Zhe Liu, Jie Feng, Bingfeng Zhou

2022

Abstract

In this paper, we propose SparseDet for end-to-end 3D object detection from point cloud. Existing works on 3D object detection rely on dense object candidates over all locations in a 3D or 2D grid following the mainstream methods for object detection in 2D images. However, this dense paradigm requires expertise in data to fulfill the gap between label and detection. As a new detection paradigm, SparseDet maintains a fixed set of learnable proposals to represent latent candidates and directly perform classification and localization for 3D objects through stacked transformers. It demonstrates that effective 3D object detection can be achieved with none of post-processing such as redundant removal and non-maximum suppression. With a properly designed network, SparseDet achieves highly competitive detection accuracy while running with a more efficient speed of 34.5 FPS. We believe this end-to-end paradigm of SparseDet will inspire new thinking on the sparsity of 3D object detection.

Paper Citation

in Harvard Style

Han J., Wan Z., Liu Z., Feng J. and Zhou B. (2022). SparseDet: Towards End-to-End 3D Object Detection. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 781-792. DOI: 10.5220/0010918000003124

in Bibtex Style

@conference{visapp22,
author={Jianhong Han and Zhaoyi Wan and Zhe Liu and Jie Feng and Bingfeng Zhou},
title={SparseDet: Towards End-to-End 3D Object Detection},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={781-792},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010918000003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - SparseDet: Towards End-to-End 3D Object Detection
SN - 978-989-758-555-5
AU - Han J.
AU - Wan Z.
AU - Liu Z.
AU - Feng J.
AU - Zhou B.
PY - 2022
SP - 781
EP - 792
DO - 10.5220/0010918000003124
PB - SciTePress