TightCap: 3D Human Shape Capture with Clothing Tightness Field

TightCap is a 3D human reconstruction dataset and framework presented at SIGGRAPH 2022 by ChenFengYe. It utilizes multi-view stereo data to capture human shapes under clothing by introducing a specialized clothing tightness field. The data supports the generation of high-fidelity clothed avatars by decoupling body shape from garment geometry.

Use Cases

• Training generative adversarial networks to predict underlying human body shapes from clothed 3D meshes
• Developing multi-view stereo algorithms for high-fidelity digital avatar creation
• Analyzing clothing deformation and fit using the clothing tightness field feature

Strengths

• Peer-reviewed SIGGRAPH 2022 methodology
• Includes unique clothing tightness field labels
• Supports multi-view stereo reconstruction tasks

Limitations

• Unknown total number of unique subjects or frames
• Restricted to controlled multi-view capture environments
• Lack of explicit license information in the source metadata

Provenance

Source

SIGGRAPH 2022 publication by ChenFengYe

Collection Method

Multi-view stereo capture and 3D scanning/reconstruction

Freshness

Last updated April 2025; based on research published in 2022.