Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversion
This work addresses depth estimation for autonomous driving and robotics, presenting an incremental improvement over existing methods.
The paper tackles the problem of limited effectiveness of sparse LiDAR hints in stereo-LiDAR depth estimation by proposing SDG-Depth, which uses a deformable propagation module to generate semi-dense hint maps and a disparity-depth conversion module to reduce triangulation errors, achieving superior performance on benchmark tests.
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.