NICE-SLAM with Adaptive Feature Grids
This work addresses memory efficiency for SLAM systems in robotics and AR/VR, but it is incremental as it builds directly on NICE-SLAM with a known optimization technique.
The paper tackles the memory explosion problem in NICE-SLAM, a dense visual SLAM system, by introducing sparse adaptive feature grids, resulting in significantly reduced memory usage while maintaining comparable reconstruction quality on the same datasets.
NICE-SLAM is a dense visual SLAM system that combines the advantages of neural implicit representations and hierarchical grid-based scene representation. However, the hierarchical grid features are densely stored, leading to memory explosion problems when adapting the framework to large scenes. In our project, we present sparse NICE-SLAM, a sparse SLAM system incorporating the idea of Voxel Hashing into NICE-SLAM framework. Instead of initializing feature grids in the whole space, voxel features near the surface are adaptively added and optimized. Experiments demonstrated that compared to NICE-SLAM algorithm, our approach takes much less memory and achieves comparable reconstruction quality on the same datasets. Our implementation is available at https://github.com/zhangganlin/NICE-SLAM-with-Adaptive-Feature-Grids.