COMO: Compact Mapping and Odometry
This addresses the problem of efficient and consistent 3D reconstruction for robotics or AR/VR applications, representing an incremental improvement in monocular SLAM methods.
The authors tackled real-time monocular mapping and odometry by developing COMO, a system that encodes dense geometry using compact 3D anchor points and per-keyframe depth covariance functions, achieving accurate pose estimation and consistent geometry in real-time.
We present COMO, a real-time monocular mapping and odometry system that encodes dense geometry via a compact set of 3D anchor points. Decoding anchor point projections into dense geometry via per-keyframe depth covariance functions guarantees that depth maps are joined together at visible anchor points. The representation enables joint optimization of camera poses and dense geometry, intrinsic 3D consistency, and efficient second-order inference. To maintain a compact yet expressive map, we introduce a frontend that leverages the covariance function for tracking and initializing potentially visually indistinct 3D points across frames. Altogether, we introduce a real-time system capable of estimating accurate poses and consistent geometry.