Det6D: A Ground-Aware Full-Pose 3D Object Detector for Improving Terrain Robustness
It addresses terrain robustness for autonomous driving, offering a plug-and-play solution but is incremental as it builds on point-based frameworks.
The paper tackles the problem of 3D object detection on sloped terrain, where existing methods degrade due to flat-world assumptions, and proposes Det6D, achieving improved robustness with full-degree-of-freedom pose prediction and a data augmentation method for non-flat scenes.
Accurate 3D object detection with LiDAR is critical for autonomous driving. Existing research is all based on the flat-world assumption. However, the actual road can be complex with steep sections, which breaks the premise. Current methods suffer from performance degradation in this case due to difficulty correctly detecting objects on sloped terrain. In this work, we propose Det6D, the first full-degree-of-freedom 3D object detector without spatial and postural limitations, to improve terrain robustness. We choose the point-based framework by founding their capability of detecting objects in the entire spatial range. To predict full-degree poses, including pitch and roll, we design a ground-aware orientation branch that leverages the local ground constraints. Given the difficulty of long-tail non-flat scene data collection and 6D pose annotation, we present Slope-Aug, a data augmentation method for synthesizing non-flat terrain from existing datasets recorded in flat scenes. Experiments on various datasets demonstrate the effectiveness and robustness of our method in different terrains. We further conducted an extended experiment to explore how the network predicts the two extra poses. The proposed modules are plug-and-play for existing point-based frameworks. The code is available at https://github.com/HITSZ-NRSL/De6D.