AI Agent Skills

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segme…

Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.

A flexible, high-performance 3D simulator for Embodied AI research.

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

3D ResNets for Action Recognition (CVPR 2018)

[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

A customisable 3D platform for agent-based AI research

An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)

Talking Head (3D): A JavaScript class for real-time lip-sync using full-body 3D avatars.

The NVIDIA VSS Blueprint is a suite of reference architectures for building GPU-accelerated vision agents and AI-powered video analytics applications.

Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition

A JavaScript framework for interactive 3D and 2D visualizations

Bringing the 3D geospatial ecosystem to Unreal Engine

WebGL Globe Data Visualization as a ThreeJS reusable 3D object