@inproceedings{e6af0af8573f4d20bbbea5392c85ed10,
title = "3D Object Detection with a Self-supervised Lidar Scene Flow Backbone",
abstract = "State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the applicability of trained models. Self-supervised training strategies can alleviate these issues by learning a general point cloud backbone model for downstream 3D vision tasks. Against this backdrop, we show the relationship between self-supervised multi-frame flow representations and single-frame 3D detection hypotheses. Our main contribution leverages learned flow and motion representations and combines a self-supervised backbone with a supervised 3D detection head. First, a self-supervised scene flow estimation model is trained with cycle consistency. Then, the point cloud encoder of this model is used as the backbone of a single-frame 3D object detection head model. This second 3D object detection model learns to utilize motion representations to distinguish dynamic objects exhibiting different movement patterns. Experiments on KITTI and nuScenes benchmarks show that the proposed self-supervised pre-training increases 3D detection performance significantly. https://github.com/emecercelik/ssl-3d-detection.git.",
keywords = "3D detection, Lidar point clouds, Scene flow, Self-supervised learning",
author = "Eme{\c c} Er{\c c}elik and Ekim Yurtsever and Mingyu Liu and Zhijie Yang and Hanzhen Zhang and Pınar Top{\c c}am and Maximilian Listl and {\c C}aylı, {Yılmaz Kaan} and Alois Knoll",
note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 17th European Conference on Computer Vision, ECCV 2022 ; Conference date: 23-10-2022 Through 27-10-2022",
year = "2022",
doi = "10.1007/978-3-031-20080-9_15",
language = "English",
isbn = "9783031200793",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "247--265",
editor = "Shai Avidan and Gabriel Brostow and Moustapha Ciss{\'e} and Farinella, {Giovanni Maria} and Tal Hassner",
booktitle = "Computer Vision – ECCV 2022 - 17th European Conference, Proceedings",
}