Deep learning-powered face swapping tool for pictures and videos
NVIDIA's GPU-accelerated streaming analytics toolkit for real-time AI video processing with TensorRT and GStreamer
Native unified multimodal AI model for understanding and generation with NEO-unify architecture
Open-source L2 ADAS stack powered by end-to-end AI for autonomous driving
Unified 6D pose estimation and tracking for novel objects using foundation models
State-of-the-art 4B parameter model for high-fidelity image-to-3D generation with PBR materials
Automate browser workflows with AI-powered computer vision and LLMs
Reusable computer vision toolkit for building AI vision applications with any model
Turn any portrait into a realistic talking head video with just audio input
Neural network-powered green screen keyer that physically unmixes foreground from background
Real-time SOTA object detection & segmentation built on DINOv2 transformers
Facebook AI Research's state-of-the-art object detection and segmentation library
Open-source autonomous driving simulator powered by Unreal Engine for AI research
Real-time face swap and deepfake creation with a single image
AI memory for your screen — record, search, and automate everything you see and do
State-of-the-art OCR model for document intelligence with multilingual support
