LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery
This addresses the need for cost-effective and reliable depth perception in autonomous robots and vehicles, representing an incremental improvement over existing methods.
The paper tackles the problem of generating accurate dense depth maps for autonomous systems by combining LIDAR and stereo imagery, using a self-supervised training approach to produce high-quality results robustly even with low-resolution inputs, potentially reducing costs.
An accurate depth map of the environment is critical to the safe operation of autonomous robots and vehicles. Currently, either light detection and ranging (LIDAR) or stereo matching algorithms are used to acquire such depth information. However, a high-resolution LIDAR is expensive and produces sparse depth map at large range; stereo matching algorithms are able to generate denser depth maps but are typically less accurate than LIDAR at long range. This paper combines these approaches together to generate high-quality dense depth maps. Unlike previous approaches that are trained using ground-truth labels, the proposed model adopts a self-supervised training process. Experiments show that the proposed method is able to generate high-quality dense depth maps and performs robustly even with low-resolution inputs. This shows the potential to reduce the cost by using LIDARs with lower resolution in concert with stereo systems while maintaining high resolution.