Radar / AI media tools / LingBot-Map
LingBot-Map: streaming 3D reconstruction foundation model (ECCV 2026 best-paper candidate)
Feed-forward 3D foundation model that reconstructs scenes from streaming video at ~20 FPS with drift correction over 10,000+ frame sequences.
Why it matters
ECCV 2026 best-paper candidacy plus a one-command interactive demo and full eval benchmarks (KITTI, Oxford Spires) make it the most accessible streaming 3D reconstruction stack open today.
What you could build with it
A real-estate media team could run the demo on a 13-minute indoor walkthrough video to generate navigable 3D point clouds for property listings, replacing per-room photos with a single streamed reconstruction.
Does it hold up?
Usable today: one-command interactive demo with bundled example scenes, offline rendering pipeline, and published eval benchmarks; third-party forks confirm reproducible runs. GPU with CUDA 12.8 and FlashInfer recommended for best results.
Built with LingBot-Map
- LingBot-Map Tutorial: GPU-Aware Inference and Point Cloud ExportMarkTechPost · Full end-to-end tutorial: installs the repo, downloads the checkpoint, runs streaming inference, and exports PLY/NPZ/GLB point clouds.
Learn more
First spotted on github: source.
More AI media tools
OpenMontage: open-source agentic video production systemTurns an AI coding assistant into a full video studio: 12 pipelines and 100+ tools for scripting, footage, narration…media · JEV 0.73HyperFramesHeyGen's open-source framework that turns HTML/CSS/GSAP into deterministic MP4 video via 21 agent skills and a router…media · JEV 0.69ArtCraft pivots to seven open-source Adobe clones built with Claude Opus 5.5Brandon Thomas pivoted his AI art IDE into a seven-app open-source creative suite…media · JEV 0.67Meshy crosses $100M ARR and launches official iOS/Android appsMeshy announced Sep 30 that ARR surpassed $100M (up 100x in under two years, first AI-3D company at that milestone)…media · JEV 0.61Kandinsky 6.0 Video: open MIT-licensed audio-video generation modelsSber's team released Kandinsky 6.0 Video: Lite (3B) and Pro (29B) diffusion models generating 5-second clips with…media · JEV 0.59FLUX 3 ImageBlack Forest Labs' new multimodal image model with bounding-box layout control, up to 10 reference images, and native…media · JEV 0.57
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.