View-tolerant identity recognition in humans depends on the stable identity cues provided by horizontal facial information.

VideoChat3, a 4-billion-parameter open-source video AI model from Nanjing University, outperforms GPT-5 and Gemini 2.5 Flash ...

Creating a realistic 3D model from a simple image remains surprisingly difficult for artificial intelligence.

Creating a new product often begins with a simple two-dimensional drawing before engineers turn it into a detailed ...

Engineers often use vision-language models to produce new designs, such as airplane or automobile components. To simulate how ...

Booz Allen CTO Bill Vass explains why the firm recently joined the Alliance for OpenUSD and its plans for a 3D repository. An ...

ZERO, Superb AI's proprietary Vision Foundation Model, takes first place overall in the CVPR 2026 Foundational Few-Shot ...

Sensor fusion combines multiple sensing modalities to improve environmental perception, obstacle avoidance, and safety in autonomous systems. AI-enabled vision and 3D depth sensing are revolutionizing ...