Atlas reconstructs Natural History Museum from just 3 input images
jnack · x · 2026-09-02
Ben Mildenhall showcased Atlas's ability to reconstruct scenes from very few inputs. He created a flythrough of London's Natural History Museum by combining only 3 input images found on Google Images from completely separate sources.
More from Multimodal
- Grok Image Generation Fail: Generates Student as Street Seller Mascot — burkov · 2026-09-02
- Five-year-old AI-generated sci-fi short 'Blightsight' resurfaces — generativist · 2026-09-02
- Atlas Reconstructs Berkeley Campanile from 10 Ground Images — petewoodbridge · 2026-09-02
- World Labs ships a new world model for 3D world generation — petewoodbridge · 2026-09-02
- An underrated alternative to Krea2 and Ideogram4: testing depth and spatial coherence — COMPLOGICGADH · 2026-09-02
- Higgsfield Launches Genjutsu: AI Video Transformation With Full Motion and Lip Sync — azed_ai · 2026-09-02