Self-supervised Visual-LiDAR Odometry with Flip Consistency
This work provides a more robust ego-motion estimation solution for autonomous vehicles and robotics operating in diverse and challenging real-world conditions, offering an incremental improvement over existing self-supervised methods.
This paper addresses the problem of ego-motion estimation, which is typically hindered by visual sensor limitations in challenging lighting or textureless environments. By integrating sparse LiDAR depth measurements with monocular images, the proposed Self-VLO framework achieves superior performance on the KITTI odometry benchmark, outperforming all self-supervised visual or LiDAR odometries and even fully supervised visual odometries.
Most learning-based methods estimate ego-motion by utilizing visual sensors, which suffer from dramatic lighting variations and textureless scenarios. In this paper, we incorporate sparse but accurate depth measurements obtained from lidars to overcome the limitation of visual methods. To this end, we design a self-supervised visual-lidar odometry (Self-VLO) framework. It takes both monocular images and sparse depth maps projected from 3D lidar points as input, and produces pose and depth estimations in an end-to-end learning manner, without using any ground truth labels. To effectively fuse two modalities, we design a two-pathway encoder to extract features from visual and depth images and fuse the encoded features with those in decoders at multiple scales by our fusion module. We also adopt a siamese architecture and design an adaptively weighted flip consistency loss to facilitate the self-supervised learning of our VLO. Experiments on the KITTI odometry benchmark show that the proposed approach outperforms all self-supervised visual or lidar odometries. It also performs better than fully supervised VOs, demonstrating the power of fusion.