MVFGA-MoCap: Multi-View Upper-Body Motion Capture for Face and Gesture Animation

MVFGA-MoCap is a multi-view upper-body motion-capture dataset collected for face and gesture animation research. It contains synchronized RGB videos of participants performing facial expressions, hand gestures, and natural upper-body communication motions, recorded using Nikon D3200 DSLR cameras at 25 FPS. The dataset was created by author 'arjavanmardi' and was last updated on the Hugging Face platform in July 2026.

Use Cases

• Train facial animation models based on synchronized multi-view video of expressions.
• Develop gesture recognition systems based on recorded hand and upper-body motions.
• Research natural human communication dynamics based on captured upper-body motion sequences.
• Benchmark multi-view reconstruction algorithms for human pose and expression.

Strengths

• Data is synchronized across multiple views, which is critical for 3D reconstruction.
• Capture setup used studio lighting and DSLR cameras, suggesting controlled recording conditions.
• Covers a specific research domain combining facial expression and gesture animation.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count, file formats, and column-level documentation are absent.
• The dataset's scale, participant demographics, and license are unknown.

Provenance

Source

Hugging Face dataset uploaded by user 'arjavanmardi'.

Collection Method

Recorded using Nikon D3200 DSLR cameras at 25 FPS with studio lighting in a multi-view setup.

Time Range

null

Freshness

Last updated 2026-07-13 15:51:31; freshness should be verified.

Geography

null