X-SLAM: Scalable Dense SLAM for Task-aware Optimization using CSFD
An algorithmic integration of simultaneous localization and mapping (SLAM) systems and follow-up vision-based tasks presents a significant challenge due to the complexity of SLAM. To address this issue, we propose X-SLAM, a real-time dense differentiable SLAM system that leverages the complex-step finite difference (CSFD) method for the efficient calculation of numerical derivatives, bypassing the need for a large-scale computational graph. The key to our approach is treating the entire SLAM process as a differentiable function, enabling the calculation of the derivatives of any variable at any time point through Taylor series expansion within the complex domain. Our system allows for the real-time calculation of not just the gradient, but also higher-order differentiation. This facilitates the use of high-order optimizers to achieve better accuracy and faster convergence. Building on the X-SLAM, we implemented end-to-end optimization frameworks for two important tasks: camera relocalization in wide outdoor scenes and active robotic scanning in complex indoor environments. Comprehensive evaluations on public benchmarks and intricate real scenes underscore the improvements in the accuracy of camera relocalization and the efficiency of robotic navigation achieved through our task-aware optimization. The source code will be released upon acceptance.
================
ACM Transactions on Graphics (SIGGRAPH), 2024
Watch video X-SLAM: Scalable Dense SLAM for Task-aware Optimization using CSFD online, duration hours minute second in high quality that is uploaded to the channel Yin Yang 27 May 2024. Share the link to the video on social media so that your subscribers and friends will also watch this video. This video clip has been viewed 91 times and liked it 7 visitors.
