⬢github Python · 17.6K ★ +132 since we first saw it · pushed 3 d ago · Apache-2.0
Robbyant/lingbot-map
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
LingBot-Map is a feed-forward 3D foundation model that performs streaming 3D reconstruction from video. Its Geometric Context Transformer unifies coordinate grounding, dense geometry, and drift correction via anchor context, a pose-reference window, and trajectory memory, running at roughly 20 FPS on sequences exceeding 10,000 frames.
Why now: It's being touted as an ECCV 2026 Best Paper Award candidate and claims state-of-the-art results over both streaming and optimization-based 3D reconstruction methods, backed by an active release cadence.
Who it is for: Researchers and engineers in 3D vision, SLAM, or robotics who need real-time reconstruction from long video streams.
Stars over our 39 snapshots: 17.5K to 17.6K, since 9 h ago.
Where people talked about it
- ⬢github Robbyant/lingbot-map just now
API: https://socialmediatrends-api.osmike.com/v1/repos/Robbyant/lingbot-map