This project is designed to work in conjunction with the SOLAMI project, providing VR visualization of SOLAMI algorithm results. SOLAMI (Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters) is a framework that enables immersive interaction with 3D autonomous characters. The SOLAMI project can be found here: SOLAMI GitHub Repository
The VR client visualizes the following capabilities of SOLAMI:
- Various character visualizations in 3D environments
- Visual comprehension of body language
- Execution of motion commands
- Engagement in interactive tasks with users
- Operating System: Windows 10/11
- VR Headset: Meta Quest 2/3/Pro or other compatible OpenXR headsets
- Unity Version: 2022.3.59f1 or later
- Additional Requirements:
- SOLAMI server running for backend processing
- Sufficient storage space for 3D assets
This project is developed using Unity 2022.3.59f1. The project requires several Unity Packages and Nuget Packages. Please install them in the following order:
- NuGetForUnity
- Meta XR All-in-One SDK
- Dynamic Bone
- Colourful Hierarchy Category GameObject
- StackExchange.Redis 2.1.58 (NuGet Package)
- WebSocketSharp-netstandard 1.0.1 (NuGet Package)
The 3D assets used in this project are sourced from Sketchfab and Vroid. These assets have been modified to fit the project's needs. The original assets can be found at:
- Late #cuterobotchallenge
- Batman Ben Affleck from The Flash 2023
- Animated Donald Trump 3D Cartoon Caricature
- Banana Cat
- Ocarina of Time Link
- Chappie Blender Rig Free
This project's code is released under the MIT License, allowing for both personal and commercial use with proper attribution.
The 3D assets sourced from Sketchfab are licensed under CC BY 4.0. According to this license, you may use these assets for any purpose (including commercial) provided you:
- Give appropriate credit to the original creators (links to original models are provided in the Intellectual Property Statement section)
- Provide a link to the CC BY 4.0 license (https://creativecommons.org/licenses/by/4.0/)
- Indicate if changes were made to the original models
The SOLAMI-VRClient utilizes SMPL-X for representing human motion and poses. Users must comply with the original license terms of SMPL-X when using this component.
This code repository is provided for research and development purposes. Users are reminded to ensure that their use of the code and included assets complies with all applicable laws and regulations.
If you find this project useful in your research, please consider citing:
@inproceedings{Jiang2025SOLAMI,
title={SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters},
author={Jianping Jiang, Weiye Xiao, Zhengyu Lin, Huaizhong Zhang, Tianxiang Ren, Yang Gao, Zhiqian Lin, Zhongang Cai, Lei Yang, Ziwei Liu},
booktitle={CVPR},
year={2025}
}
@inproceedings{Cai2024DLP,
title={Digital Life Project: Autonomous 3D Characters with Social Intelligence},
author={Zhongang Cai, Jianping Jiang, Zhongfei Qing, Xinying Guo, Mingyuan Zhang, Zhengyu Lin, Haiyi Mei, Chen Wei, Ruisi Wang, Wanqi Yin, Xiangyu Fan, Han Du, Liang Pan, Peng Gao, Zhitao Yang, Yang Gao, Jiaqi Li, Tianxiang Ren, Yukun Wei, Xiaogang Wang, Chen Change Loy, Lei Yang, Ziwei Liu},
booktitle={CVPR},
year={2024}
}
Our SOLAMI-VRClient is the VR client implementation for the SOLAMI framework. The core SOLAMI implementation is based on AnyGPT, HumanTOMATO, and MotionGPT.