newsHacker NewsTrust 52 · CommunityPublished 1mo agoLive · 1mo ago
Lingbot-map: A 3D foundation model for reconstructing scenes from streaming data
14points0comments
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%Wat3R: Underwater 3D Geometry Learning without Annotations →
- PossiblePossibly related (embedding) · 50%ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space →
- PossiblePossibly related (embedding) · 48%PointSplat: Compact Gaussian Splatting via Human-Centric Prediction →
- PossiblePossibly related (embedding) · 48%Native Video-Action Pretraining for Generalizable Robot Control →
- PossiblePossibly related (embedding) · 45%MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos →
- PossiblePossibly related (embedding) · 48%scenepilotLLM/scenepilot →
- PossiblePossibly related (embedding) · 53%Toward Semantic Communication for Real-time Mobile 3D Reconstruction →
Covers
paperWat3R: Underwater 3D Geometry Learning without AnnotationspaperABot-3DWorld 0: A Universal World Model to Explore Any 3D SpacepaperPointSplat: Compact Gaussian Splatting via Human-Centric PredictionpaperNative Video-Action Pretraining for Generalizable Robot ControlpaperMAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos
Covers (incoming)
Related across the graph
paperToward Semantic Communication for Real-time Mobile 3D ReconstructionpaperMAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB VideospaperWat3R: Underwater 3D Geometry Learning without AnnotationspaperNative Video-Action Pretraining for Generalizable Robot ControlreposcenepilotLLM/scenepilotpaperPointSplat: Compact Gaussian Splatting via Human-Centric PredictionpaperABot-3DWorld 0: A Universal World Model to Explore Any 3D Space