Computer Vision

Image Processing Image Recognition Visual Perception Visual Recognition Image Analysis Vision-Language Processing 3D Reconstruction Video Analysis Natural Language Processing Facial Recognition

Google Rolls Out SL2T to Translate ASL to Text on Pixel 11

The feature converts upper-body video into on-device landmark coordinates that Google discards before sending them for cloud translation.

Mistral Releases Robostral Navigate, an 8B Model That Guides Robots With a Single RGB Camera

AI Study Points to Different Holbein Drawing as the True Anne Boleyn

AI 'Mirrors' Give Blind Users Detailed Appearance Feedback

Amap Launches ‘Flying Street View’ 3D Tours, Opening Free Access to 1 Million Businesses

Meta Launches SAM 3 and SAM 3D for Text-Driven Segmentation and Single-Image 3D

Wayve in Talks With Microsoft and SoftBank on Up to $2 Billion Raise

RealSense Completes Spinout From Intel With $50 Million Series A

Most Computer Vision Research Powers Surveillance, Study Finds

Study Reveals AI’s Persistent Struggle with Dynamic Social Interactions

Google Expands Gemini AI with Google Photos Integration on Android

MIT Develops Clio to Enhance Robots' Task-Specific Object Recognition

Mistral Unveils Pixtral 12B, Its First Multimodal AI Model

Mobileye Halts LiDAR Development, Cuts 100 Jobs

Google's DeepMind Robot Reaches Amateur Level in Table Tennis

Pinterest Introduces Size-Inclusive 'Body Type Ranges' Tool in the U.S.