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
- Midjourney dual --sref combo produces medieval woodcut cat knight art — sergeantsref · 2026-11-02
- Fluffy AI-generated character designs: fox girl, alien bug and cat photographer — OVolosin82152 · 2026-11-02
- Fable 5.5 reportedly one-shots animation in pure code as Anthropic's coding bet pays off — Hesamation · 2026-11-02
- FlowHMR gets 5x faster, demoing an LLM agent pipeline from video to photoreal mocap — camenduru · 2026-11-02
- Retro 1973 music video "Rock is Dead" by TECHHALLA showcases startlingly realistic AI generation — Mother-Pear-2392 · 2026-11-02
- Weekend splatting with COLMAP and Lichtfeld — janusch_patas · 2026-11-02