A team of archaeologists led by researchers from Binghamton University has combined over 22,000 images of the primary quarry on Rapa Nui (Easter Island) to create the first-ever interactive 3D model ...

We propose WorldGrow — a generative method which creates infinite EXPLICIT 3D worlds, an alternative to the extensible, realistic, interactive world simulator. We provide an example script ...

Sports Interactive and FIFA have signed a new multi-year partnership to bring official licences for FIFA's "biggest competitions to the Football Manager series, including the FIFA World Cup 26 held in ...

Gabriel has been playing games since he was a kid. Loves most RPG games, platformers, and innovative indie games, and can talk for hours about how the first Fallout is the greatest game ever. He ...

On Tuesday, Tencent released HunyuanWorld-Voyager, a new open-weights AI model that generates 3D-consistent video sequences from a single image, allowing users to pilot a camera path to “explore” ...

Abstract: Envisioning physically plausible outcomes from a single image requires a deep understanding of the world’s dynamics. To address this, we introduce PhysGen3D, a novel framework that ...

A new research framework helps AI agents explore three-dimensional spaces they can’t directly detect. Called MindJourney, the approach addresses a key limitation in vision-language models (VLMs), ...

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...

Google’s Genie 3 can generate a range of 3D environments. Courtesy Google DeepMind Biking on a narrow mountain road in India, driving through volcanic terrain and wingsuit flying over the Alps—these ...

Google DeepMind has revealed Genie 3, a new AI model that builds playable 3D worlds from simple text commands. Announced Tuesday, the system creates these interactive environments in real time, a ...