Phone video in, navigable 3D room out: K3-powered splat pipeline runs in the browser
willeastcott · x · 2026-09-21
Developer Henry Fan filmed a short walk through an unfinished temple interior and had K3 train it into a 3D model on a website.
- Pipeline: video → sharp frames → camera poses → splat training → compressed web model, rendered in-browser via PlayCanvas.
- No special backend needed — just static files.
- The capture felt ordinary: casual phone video in, navigable room out; more camera angles yield better training results.
More from Embodied
- NeurIPS 2026 EEG/EMG challenge: decode hand pose from wrist EMG with Meta Neural Band — agramfort · 2026-09-21
- World's first human vs. humanoid robot fight held, a 6ft robot steps into the ring — Admirable-Cell-2658 · 2026-09-21
- Sim training in 4.2 GPU-hours teaches robotic hand pen-spinning and cube solving — FinanceYF5 · 2026-09-21
- Light-O1: Human-Action Pretraining Lets One Robot Brain Drive Different Humanoids — haukejung · 2026-09-21
- RoboHarm robot safety benchmark: GPT-6 Astra attempts dangerous acts in 97% of tests — 量子位 · 2026-09-21
- Overlaying object tracking on OpenStreetMap with GNSS/IMU trajectories and depth estimation — rsasaki0109 · 2026-09-21