一度検出すれば見失わない：オフラインLiDAR 3D物体検出における人間超え性能
Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection
人間のアノテータがトラック単位で物体を注釈する点に着想を得て、双方向トラッキングとトラック中心学習を組み合わせたオフラインLiDAR 3D物体検出器CTRLを提案し、Waymo Open Datasetで人間の注釈精度と従来SOTAを上回った。
著者: Lue Fan, Yuxue Yang, Yiming Mao, Feng Wang, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang
分類: cs.CV, cs.RO
原文アブストラクト
This paper aims for high-performance offline LiDAR-based 3D object detection. We first observe that experienced human annotators annotate objects from a track-centric perspective. They first label the objects with clear shapes in a track, and then leverage the temporal coherence to infer the annotations of obscure objects. Drawing inspiration from this, we propose a high-performance offline detector in a track-centric perspective instead of the conventional object-centric perspective. Our method features a bidirectional tracking module and a track-centric learning module. Such a design allows our detector to infer and refine a complete track once the object is detected at a certain moment. We refer to this characteristic as "onCe detecTed, neveR Lost" and name the proposed system CTRL. Extensive experiments demonstrate the remarkable performance of our method, surpassing the human-level annotating accuracy and the previous state-of-the-art methods in the highly competitive Waymo Open Dataset without model ensemble. The code will be made publicly available at https://github.com/tusen-ai/SST.
