Radar / AI media tools / Horizon LoFT

Horizon LoFT: a video-geometry foundation model for 3D scene recovery

Horizon Robotics Lab's native video-geometry foundation model jointly predicts camera pose, intrinsics and per-frame depth from RGB video to recover 3D scene structure, trained on about 2.97M sequences and 962M frames.

new launchmedia · 3dadded 2026-11-19
Open Horizon LoFT →View on the radar

Why it matters

A Chinese robotics lab's geometry foundation model aimed at embodied AI spatial perception — the 3D-world-modeling layer for robots.

What you could build with it

A robotics team could feed ordinary video from a robot's camera through this model to recover a 3D map of a room — camera positions and depth included — without lidar hardware, and use that map for navigation and manipulation planning.

Does it hold up?

Too early to judge: the benchmark claims are the authors' own and no public weights or independent evaluations have surfaced yet.

Built with Horizon LoFT

Learn more

launch coverage →

First spotted on article: source.

More AI media tools

Hyperframes: write HTML, render video — HeyGen's open video engine for AI agentsOpen-source renderer from HeyGen that turns HTML, CSS and JavaScript into MP4 video, built so AI coding agents can…media · JEV 0.78FastFrames: Apple's open video models that generate frames in 36 msApple and Cornell's family of autoregressive video diffusion models that generate 480p frames at interactive latency…media · JEV 0.57HeyGen Avatar 6: an audio-driven avatar model with script-aware gesturesHeyGen's next-generation audio-driven personal avatar model — script-aware gestures, native 2K output, a personal…media · JEV 0.52Kling Image 4.0: native 8K images with 2,000 characters of clean textKuaishou's Kling Image 4.0 generates natively in 8K, renders up to 2,000 characters of legible text in one image, and…media · JEV 0.48Suno Visuals: AI music videos and album art for your songsSuno's new Visuals feature turns songs into lyric videos with lip-sync, album art, and clips up to 15 seconds that…media · JEV 0.46MAI Image 2.7: Microsoft's image editor tops the leaderboard at a fifth of the priceMicrosoft's MAI Image 2.7 leads Artificial Analysis's image-editing leaderboard at 1,215 Elo — ahead of GPT Image 2.6…media · JEV 0.46

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.