SpatialVLM spatial VQA data

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

• id: spatialvlm-spatial-vqa-data
• kind: language and reasoning annotation
• robot or device: internet real-world images (class: sensor only)
• how collected: automatic 3D spatial VQA generation
• size as stated: 2 billion VQA examples on 10 million real-world images
• hours: not stated | hours only claimed: none | episodes: not stated
• year: 2024
• organisation: not stated
• licence: not stated (class: not stated)
• access: not stated (class: not stated)
• link (paper): https://arxiv.org/abs/2401.12168
• note: No download located; community reproductions listed separately.

Confirm the licence at the link before relying on it.