3DGS SLAM

The field studies how a camera can track its motion while incrementally building a detailed, view-renderable 3D map from images and other sensors. Systems optimize Gaussian maps and camera poses using photometric and geometric cues, with approaches spanning monocular, RGB-D, visual-inertial, and LiDAR setups; some add learned depth or pose priors, loop closure, semantic features, or uncertainty estimates. Work also extends Gaussian maps to dynamic and deformable scenes, and commonly evaluates tracking and rendering on benchmarks such as TUM RGB-D, Replica, ScanNet, and KITTI. A central tension is balancing map quality and robust global tracking against optimization time, memory use, and reliability in challenging conditions such as motion, blur, and large outdoor scenes.