AI Agent Skills

Segment-Anything + 3D. Let's lift anything to 3D.

UMI-3D SLAM and Data Processing Pipeline: https://umi-3d.github.io/

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

3D ResNets for Action Recognition (CVPR 2018)

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.

Video classification tools using 3D ResNet

An open survey on 3D Gaussian Splatting compression methods

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.

A customisable 3D platform for agent-based AI research

[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…

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

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

A JavaScript framework for interactive 3D and 2D visualizations

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

Bringing the 3D geospatial ecosystem to Unreal Engine