Robustness Meets Deep Learning: An End-to-End Hybrid Pipeline for Unsupervised Learning of Egomotion
This addresses camera pose estimation for robotics/autonomous vehicles, but is incremental as it combines existing techniques in a novel pipeline.
The authors tackled the problem of unsupervised learning of camera motion (egomotion) by combining deep learning predictions for optical flow and disparity with model-based optimization, achieving state-of-the-art results on the KITTI dataset even with independently moving objects.
In this work, we propose a method that combines unsupervised deep learning predictions for optical flow and monocular disparity with a model based optimization procedure for instantaneous camera pose. Given the flow and disparity predictions from the network, we apply a RANSAC outlier rejection scheme to find an inlier set of flows and disparities, which we use to solve for the relative camera pose in a least squares fashion. We show that this pipeline is fully differentiable, allowing us to combine the pose with the network outputs as an additional unsupervised training loss to further refine the predicted flows and disparities. This method not only allows us to directly regress relative pose from the network outputs, but also automatically segments away pixels that do not fit the rigid scene assumptions that many unsupervised structure from motion methods apply, such as on independently moving objects. We evaluate our method on the KITTI dataset, and demonstrate state of the art results, even in the presence of challenging independently moving objects.