3D VQA

Three-dimensional visual question answering (VQA) asks models to answer questions that require understanding objects, layouts, distances, viewpoints, or events in 3D scenes and volumes. Systems combine language models with point clouds, RGB-D images, multiview video, or reconstructed scene representations such as occupancy maps and scene graphs; some also use geometric tools to measure or retrieve relevant evidence. Benchmarks such as ScanQA and SQA3D test scene understanding and spatial reasoning, while medical VQA evaluates reasoning over volumetric scans. A central challenge is ensuring answers are grounded in 3D evidence rather than language or visual shortcuts, while making reasoning over many views accurate and efficient.