Abstract:

Most existing deep learning-based depth completion methods are only suitable for high (e.g. 64-scanline) resolution LiDAR measurements. However, it is of great interest to reduce the number of LiDAR channels in many aspects (cost, weight of a device, power consumption). In this paper, we propose a new depth completion framework with various LiDAR scanline resolutions, which performs as well as methods built for 64-scanline resolution LiDAR inputs. For this, we define a consistency loss between the predictions from LiDAR measurements of different scanline resolutions. Also, we design a fusion module to integrate features from different modalities