Agent S: an open agentic framework that uses computers like a human

This is a curated list of "Embodied AI or robot with Large Language Models" research. Watch this repository for the latest updates! 🔥

A list of AI autonomous agents

Robust Speech Recognition via Large-Scale Weak Supervision

A fast, local neural text to speech system

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

the AI-native open-source embedding database

Header only, single file, simple and efficient C++11 library to compute the signed distance function (SDF) to a triangle mesh

Neural Unsigned Distance Fields (NDF) - Codebase

Official implementation for the CVPR'23 paper: Visibility Aware Human-Object Interaction Tracking from Single RGB Camera

Official implementation for the paper CHORE, ECCV'22

code release of paper "DIMOS: Synthesizing Diverse Human Motions in 3D Indoor Scenes"

Estimate vertex-level 3D human-scene and human-object contacts across the full body mesh

Humos paper repository

(CVPR 2023) Pytorch implementation of “T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations”

Data preparation and loader for AMASS

Official Implementation of SIGGRAPH Asia 2023 (TOG) Paper: Object Motion Guided Human Motion Synthesis

The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .

Official PyTorch implementation of EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views

[CVPR'23] Method to infer objects from human interactions

[CVPR 2023] Detecting Human-Object Contact in Images

Official implementation of CVPR24 highlight paper "Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance"

Official Pytorch implementation for 2020 3DV paper "PLACE: Proximity Learning of Articulation and Contact in 3D Environments" and trained models

"IMoS: Intent-Driven Fullbody Motion Synthesis for Human-Object Interaction". Proceeding of EUROGRAPHICS 2023.

Code for paper 'Hand-Object Contact Consistency Reasoning for Human Grasps Generation' at ICCV 2021

Official implementation of TeSMo, a method for text-controlled scene-aware motion generation, from the ECCV 2024 paper: "Generating Human Interaction Motions in Scenes with Text Control".

Lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender.

Resolving 3D Human Pose Ambiguities with 3D Scene Constraints https://prox.is.tue.mpg.de