World Labs: 3D scene reconstruction needs drop from hundreds of photos to just ~3
airesearch12 · x · 2026-09-16
- Ben Mildenhall of World Labs said in a16z's Sep 4 interview that the number of photos needed to build an explorable 3D scene is being cut from hundreds to roughly 3 — a 50-100x reduction.
- This turns imagery and internet photos into explorable scenes at scale.
- The poster adds that with upcoming techniques, a few photos or video frames will reconstruct a full 3D model of any room, unlocking new app categories.
More from Multimodal
- Boreal by Creatify lands on fal: prompt-to-ad videos at 2K, up to 20s — Scobleizer · 2026-09-16
- YuE2 on an RTX 5070 Ti generates a 4-minute song in 130 seconds — Downtown-Cover-7422 · 2026-09-16
- LAION-backed voice acting arena lets you blind-compare TTS models performing the same scene — realmrfakename · 2026-09-16
- Hugging Face releases a beginner-friendly visual guide to flow matching — Hugging Face · 2026-09-16
- Two friends made an 8-minute AI action comedy, playing both leads — Muted_Camp352 · 2026-09-16
- Stunning Three.js+TSL Coastal World 'Tideglass Cove' Released Open Source — techartist_ · 2026-09-16