DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior
This addresses the deployment challenge of Gaussian SLAM in real-world robotic systems operating under sparse-view conditions, representing a hybrid incremental improvement.
The paper tackles the problem of Gaussian SLAM systems requiring extensive keyframes for dense reconstruction, which is impractical for sparse-view robotic applications. DenseSplat combines NeRF priors with 3DGS to fill map gaps using sparse keyframes, achieving superior tracking and mapping performance compared to state-of-the-art methods on large-scale datasets.
Gaussian SLAM systems excel in real-time rendering and fine-grained reconstruction compared to NeRF-based systems. However, their reliance on extensive keyframes is impractical for deployment in real-world robotic systems, which typically operate under sparse-view conditions that can result in substantial holes in the map. To address these challenges, we introduce DenseSplat, the first SLAM system that effectively combines the advantages of NeRF and 3DGS. DenseSplat utilizes sparse keyframes and NeRF priors for initializing primitives that densely populate maps and seamlessly fill gaps. It also implements geometry-aware primitive sampling and pruning strategies to manage granularity and enhance rendering efficiency. Moreover, DenseSplat integrates loop closure and bundle adjustment, significantly enhancing frame-to-frame tracking accuracy. Extensive experiments on multiple large-scale datasets demonstrate that DenseSplat achieves superior performance in tracking and mapping compared to current state-of-the-art methods.