VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residuals

Abstract

We propose a dense indirect visual odometry method taking as input externally estimated optical flow fields instead of hand-crafted feature correspondences. We define our problem as a probabilistic model and develop a generalized-EM formulation for the joint inference of camera motion, pixel depth, and motion-track confidence. Contrary to traditional methods assuming Gaussian-distributed observation errors, we supervise our inference framework under an (empirically validated) adaptive log-logistic distribution model. Moreover, the log-logistic residual model generalizes well to different state-of-the-art optical flow methods, making our approach modular and agnostic to the choice of optical flow estimators. Our method achieved top-ranking results on both TUM RGB-D and KITTI odometry benchmarks. Our open-sourced implementation is inherently GPU-friendly with only linear computational and storage growth.

arXiv commentPaper was accepted to CVPR20. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. The arxiv version fixed a few typos

References in corpus (6)

• DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
• DeMoN: Depth and Motion Network for Learning Monocular Stereo
• End-to-End Learning of Geometry and Context for Deep Stereo Regression
• BA-Net: Dense Bundle Adjustment Network
• Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth
• LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo