TurboMap: GPU-Accelerated Local Mapping for Visual SLAM
This work addresses real-time performance bottlenecks in Visual SLAM for robotics and AR/VR applications, representing an incremental improvement with specific optimizations.
The paper tackled the challenge of reducing latency in local mapping for Visual SLAM systems by developing TurboMap, a GPU-parallelized and CPU-optimized backend, achieving average speedups of 1.3x on EuRoC and 1.6x on TUM-VI datasets while maintaining accuracy.
In real-time Visual SLAM systems, local mapping must operate under strict latency constraints, as delays degrade map quality and increase the risk of tracking failure. GPU parallelization offers a promising way to reduce latency. However, parallelizing local mapping is challenging due to synchronized shared-state updates and the overhead of transferring large map data structures to the GPU. This paper presents TurboMap, a GPU-parallelized and CPU-optimized local mapping backend that holistically addresses these challenges. We restructure Map Point Creation to enable parallel Keypoint Correspondence Search on the GPU, redesign and parallelize Map Point Fusion, optimize Redundant Keyframe Culling on the CPU, and integrate a fast GPU-based Local Bundle Adjustment solver. To minimize data transfer and synchronization costs, we introduce persistent GPU-resident keyframe storage. Experiments on the EuRoC and TUM-VI datasets show average local mapping speedups of 1.3x and 1.6x, respectively, while preserving accuracy.