Tag
58 articles
This article explains the advanced AI and computer vision technologies behind Meta's Ray-Ban Smart Glasses, including neural networks, edge computing, and adaptive optical systems.
Learn how to repurpose pre-trained video generators for classic computer vision tasks like depth estimation and semantic segmentation, demonstrating the potential of video generators as universal world models.
NVIDIA's DeepStream 9.1 introduces agentic AI capabilities that allow natural language prompts to construct complex video analytics pipelines, while advancing multi-view 3D tracking and automated camera calibration.
This article explains how advanced AI techniques were used to reconstruct a legendary football goal that was never filmed, demonstrating the power of AI in motion reconstruction and historical preservation.
Learn how to build a basic visual AI image classifier using pre-trained machine learning models. This beginner-friendly tutorial walks you through setting up your environment and creating an AI system that can identify objects in photos.
This explainer explores how advanced AI technologies in AR glasses blur the line between real and artificial reality, examining the neural rendering techniques that make this possible and the philosophical implications of perceptual ambiguity.
Learn to build a simplified world model inspired by China's Orca system that predicts abstract world states without requiring labeled action data, demonstrating how unsupervised learning can reduce data requirements in robotics.
Learn to build a basic automated monitoring system similar to Waymo's technology that can detect suspicious activities in vehicles and trigger alerts.
Mistral AI enters robotics with Robostral Navigate, an 8B model that navigates robots using only a single camera, showcasing a significant step toward affordable, real-world robotics.
Learn to build a vision-language-action model for warehouse robotics that can reduce human intervention by half, similar to Nomagic's breakthrough implementation.
Learn to build a privacy protection system for smart glasses that can automatically detect when privacy covers are in place using computer vision and template matching techniques.
Learn how LingBot-Vision, an open-source AI model from Ant Group, uses boundary-focused learning to understand spatial relationships in images, with applications in robotics, self-driving cars, and more.
