Horizon Robotics Announces LoFT Video Geometry Model, With Paper, Code and Weights Pending
- Published
- Source
- PanDaily.com
Horizon Robotics has announced LoFT, a model for reconstructing geometry from video. The company’s paper, code and model weights remain pending, so the announcement does not yet provide those resources for independent review or use. The reported results are attributed to the team; the source does not disclose specific performance figures.
LoFT’s focus on video geometry reconstruction places the announcement in the area of methods that derive spatial structure from visual sequences. For engineers and enterprise decision makers, access to the paper, code and weights will be important for assessing the approach, reproducing the team-reported results and determining its technical relevance. The source does not specify an application sector, deployment, or commercial availability.
Horizon Robotics has not disclosed when the paper, code or weights will be released. Their publication, alongside details supporting the team-reported results, remains the specific milestone to monitor. Until those materials are available, the model’s methodology and reported performance cannot be independently assessed from the information provided.
Original report
Horizon Robotics Announces LoFT Video Geometry Model With Resources Still Pending
PanDaily.com · [email protected] (Pandaily)This briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
Related Suppliers
Horizon Robotics 地平线
Chinese developer of automotive AI compute chips and software for ADAS and autonomous driving.
Loft Orbital
US space infrastructure firm operating shared YAM satellite buses that hosted the first onboard demo of Google DeepMind's Gemma AI model in orbit.
D-Robotics 地瓜机器人
Chinese robotics computing platform spun off from Horizon Robotics in 2024, providing RDK AI boards with 5-80+ TOPS BPU for embodied intelligence.
Aether AI
Seed-stage San Diego startup building causal world models that predict action outcomes, with robotics as its first target market.
Maxinsights
San Francisco vendor, founded 2024, of annotated egocentric video, hand/body mocap and tactile data for training robot VLA and world action models.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.