Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
This addresses the problem of object detection in 3D point clouds for applications like autonomous driving, though it appears incremental as it builds on existing domain adaptation ideas.
The paper tackles the challenge of robust feature representation for 3D point cloud object detection by proposing a domain adaptation approach that bridges perceptual and conceptual domains, achieving state-of-the-art results.
Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to sensors, appearance of a same object varies a lot in point cloud data. Designing robust feature representation against such appearance changes is hence the key issue in a 3D object detection method. In this paper, we innovatively propose a domain adaptation like approach to enhance the robustness of the feature representation. More specifically, we bridge the gap between the perceptual domain where the feature comes from a real scene and the conceptual domain where the feature is extracted from an augmented scene consisting of non-occlusion point cloud rich of detailed information. This domain adaptation approach mimics the functionality of the human brain when proceeding object perception. Extensive experiments demonstrate that our simple yet effective approach fundamentally boosts the performance of 3D point cloud object detection and achieves the state-of-the-art results.