Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversion

TL;DR

This paper introduces SDG-Depth, a novel stereo-LiDAR depth estimation network that uses deformable propagation and learned disparity-depth conversion to improve accuracy and efficiency in autonomous driving and robotic perception.

Contribution

The paper proposes a semi-dense hint guidance network with deformable propagation and a disparity-depth conversion module, advancing stereo-LiDAR depth estimation methods.

Findings

Outperforms existing methods on benchmark tests

Provides accurate depth estimation in distant regions

Efficient in computation and deployment

Abstract

Accurate and dense depth estimation with stereo cameras and LiDAR is an important task for automatic driving and robotic perception. While sparse hints from LiDAR points have improved cost aggregation in stereo matching, their effectiveness is limited by the low density and non-uniform distribution. To address this issue, we propose a novel stereo-LiDAR depth estimation network with Semi-Dense hint Guidance, named SDG-Depth. Our network includes a deformable propagation module for generating a semi-dense hint map and a confidence map by propagating sparse hints using a learned deformable window. These maps then guide cost aggregation in stereo matching. To reduce the triangulation error in depth recovery from disparity, especially in distant regions, we introduce a disparity-depth conversion module. Our method is both accurate and efficient. The experimental results on benchmark tests show its superior performance. Our code is available at https://github.com/SJTU-ViSYS/SDG-Depth.