1 repository
Maintains stable geometry and camera pose alignment across thousands of frames by combining coordinate grounding, dense geometric cues, and trajectory memory.
Distinct from Long-Context Sequence Processors: Distinct from Long-Context Sequence Processors: corrects spatial drift in 3D reconstructions rather than managing token windows for text.
Explore 1 awesome GitHub repository matching data & databases · 3D Drift Correctors. Refine with filters or upvote what's useful.
Lingbot-map is a feed-forward neural network designed for real-time 3D scene reconstruction from streaming video. It processes video frames one at a time without iterative optimization, producing dense geometry and camera poses at interactive frame rates directly from a live feed. The project distinguishes itself through its ability to maintain stable geometry and pose alignment across very long video sequences, handling thousands of frames without drift. It achieves this through a combination of coordinate grounding memory, sliding-window inference with overlapping keyframes, and a paged KV
Provides drift correction that maintains stable geometry and pose alignment across thousands of video frames.