Confidence Guided Stereo 3D Object Detection with Split Depth Estimation [article]

Chengyao Li, Jason Ku, Steven L. Waslander
2020 arXiv   pre-print
Accurate and reliable 3D object detection is vital to safe autonomous driving. Despite recent developments, the performance gap between stereo-based methods and LiDAR-based methods is still considerable. Accurate depth estimation is crucial to the performance of stereo-based 3D object detection methods, particularly for those pixels associated with objects in the foreground. Moreover, stereo-based methods suffer from high variance in the depth estimation accuracy, which is often not considered
more » ... n the object detection pipeline. To tackle these two issues, we propose CG-Stereo, a confidence-guided stereo 3D object detection pipeline that uses separate decoders for foreground and background pixels during depth estimation, and leverages the confidence estimation from the depth estimation network as a soft attention mechanism in the 3D object detector. Our approach outperforms all state-of-the-art stereo-based 3D detectors on the KITTI benchmark.
arXiv:2003.05505v1 fatcat:twhxab5ogrdcvhae6bjjh5dmde