COMO: Compact Mapping and Odometry

arXiv:2404.03531v1 Announce Type: new
Abstract: 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 …

abstract anchor arxiv compact covariance cs.cv decoding functions geometry mapping maps optimization per real-time representation set together type via