HOT RADAR
llmHEAT 9.5°

AI CURATED HOT STORY · 11/19/2026

Horizon Robotics Releases LoFT Video Geometry Foundation Model

1 reports archived1 independent sourcesupdated 11/19/2026, 07:30:03
Synthesis & Latest Updates
1 Sources Cross-Validated

Horizon Robotics' research lab released LoFT, a native video geometry foundation model built on a dual-loop Transformer that jointly predicts camera pose, intrinsics and per-frame depth from RGB video to recover 3D scene structure. Trained on roughly 2.97 million sequences and 962 million frames, it reports state-of-the-art results across SpatialBench, ClassicBench and VRBench, targeting robotic spatial perception and embodied learning.

LATEST/Horizon Robotics' research lab released LoFT, a native video geometry foundation model built on a dual-loop Transformer that jointly predicts camera pose, intrinsics and per-frame depth from RGB video to recover 3D scene structure. Trained on roughly 2.97 million sequences and 962 million frames, it reports state-of-the-art results across SpatialBench, ClassicBench and VRBench, targeting robotic spatial perception and embodied learning.

Hourly heat curve

9 fully observed hours
Now
9.5
Peak
11.609:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first
  1. IT之家 · 智能时代T2·78 pts
    • The dual-loop Transformer decouples cross-frame feature aggregation from iterative camera-state refinement, feeding pose and intrinsics back into the next loop
    • The training platform aggregates about 2.97 million sequences and 962 million frames spanning simulated and real, dynamic and static scenes
    • It reports state-of-the-art results on SpatialBench, ClassicBench and VRBench