# VisTa3D

From the catalogue. Listed by one researcher from one source page.

- id: `vista3d`
- kind: 3D assets and scenes
- robot or device: RGB, depth, tactile response maps, IMU, laser-scan ground truth (class: sensor only)
- how collected: handheld capture of thin objects
- size as stated: 387 scenes, 70 thin objects
- hours: not stated | hours only claimed: none | episodes: not stated
- year: 2026
- organisation: not stated
- licence: MIT (class: open)
- access: open (class: open)
- link (dataset): https://huggingface.co/datasets/shaniaguo/VisTa3D
- Hugging Face repository: `shaniaguo/VisTa3D`, 9,575 downloads in 30 days, https://huggingface.co/datasets/shaniaguo/VisTa3D
- note: Thin object reconstruction from vision and touch.

Confirm the licence at the link before relying on it.