[CVPR 2022] HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction

Graph Neural Network Library for PyTorch

⭕️ Official codes for "SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction" (CVPR2024)

Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]

[ECCV 2022] Official implementation of the paper "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos"

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

Implementation of a Trust Region Newton Conjugate Gradient optimizer in Pytorch

MPI-IS Mesh Processing Library

a fish-shaped wireless ergonomic split keyboard

Make websites accessible for AI agents

Simulating SMPL humanoid, supporting PHC/PHC-MJX/PULSE/SimXR code bases.

A generative world for general-purpose robotics & embodied AI learning.

Simulations for TurtleBot3

Massively parallel rigidbody physics simulation on accelerator hardware.

Official Implementation of the ICLR 2024 spotlight paper: Universal Humanoid Motion Representations for Physics-Based Control

[ECCV 2024] This is the official implementation of PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Driving

Fast and memory-efficient exact attention

[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"

[ICCV 2023] SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving

[ICLR 2023] DiffMimic: Efficient Motion Mimicking with Differentiable Physics https://arxiv.org/abs/2304.03274

[ICRA19] Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

Tools to load, process and visualize motion capture data

Physics-based Character Controllers Using Conditional VAEs (SIGGRAPH 2022)

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

Toolkit for EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild

Code for: "Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation" Accepted @ ECCV2022

A paper list of my history reading. Robotics, Learning, Vision.