Recently, innovative company Meshcapade in the field of 3D digital human modeling has garnered industry attention with its groundbreaking technology for generating human motion. By compressing complex human behaviors into a parameterized model of 100 digital parameters known as SMPL, the company is redefining the future of digital human modeling.
As a subsidiary of the Max Planck Institute for Intelligent Systems in Tübingen, Meshcapade has rapidly grown since its establishment in 2018 to become a leading enterprise in the 3D human technology sector. Its clientele now spans various sectors including fashion, fitness, AR/VR, telepresence, and entertainment, including six of the top ten companies on the NASDAQ.
The core technology of the company, SMPL (Skinned Multi-Person Linear model), has broken the limitations of traditional motion capture. Co-founder Michael J. Black noted, "SMPL is constructed using standard computer graphics technology, achieving higher accuracy and operational efficiency through machine learning, while maintaining full compatibility with existing systems."
Meshcapade's innovation lies in its unique method of motion generation. Users only need to input text prompts, and the system can generate multiple animation suggestions, supporting export in FBX or GLB formats, which can be directly applied to animation and video creation tools. This convenience greatly simplifies the 3D animation production process.
Compared to traditional motion capture technology, Meshcapade's solution does not require specialized motion capture clothing or controlled environments. The system can extract 3D human motion data from any video and intelligently consider surrounding environmental factors, making the generated motions more natural and fluid.
To promote industry development, Meshcapade has made the SMPL technology freely available for academic use, fostering an active community of researchers and developers. With the continuous improvement of the technology and the growing community, Meshcapade is opening up new possibilities in the field of digital human modeling.
Address: https://me.meshcapade.com/