VOLDOR-SLAM: For the Times When Feature-Based or Direct Methods Are Not Good Enough
This addresses the need for accurate and robust camera pose estimation in SLAM applications when feature-based or direct methods are insufficient, though it appears incremental as it extends an existing model.
The paper tackles the problem of robust visual SLAM by developing VOLDOR-SLAM, a dense-indirect system that uses external dense optical flows as input, achieving online operation at around 15 FPS on a single GTX1080Ti GPU while constructing globally-consistent dense maps.
We present a dense-indirect SLAM system using external dense optical flows as input. We extend the recent probabilistic visual odometry model VOLDOR [Min et al. CVPR'20], by incorporating the use of geometric priors to 1) robustly bootstrap estimation from monocular capture, while 2) seamlessly supporting stereo and/or RGB-D input imagery. Our customized back-end tightly couples our intermediate geometric estimates with an adaptive priority scheme managing the connectivity of an incremental pose graph. We leverage recent advances in dense optical flow methods to achieve accurate and robust camera pose estimates, while constructing fine-grain globally-consistent dense environmental maps. Our open source implementation [https://github.com/htkseason/VOLDOR] operates online at around 15 FPS on a single GTX1080Ti GPU.