MindView: Benchmarking Generative Multi-View Spatial Intelligence
[Widzenie komputerowe] Autorzy: Yanbo Wang, Siqi Luo, Siyu Zhang i 9 więcej
Spatial intelligence has recently been assessed through generative tasks such as spatially grounded image editing, yet language-guided generation of spatially consistent views from partial multi-view observations remains underexplored. We introduce MindView, a benchmark for generative multi-view spatial intelligence with 1,500 samples from 513 scenes across three indoor datasets. Its seven tasks form two families: geometry-dominant tasks specify changes in camera position and orientation, while semantics-dominant tasks require inferring target viewpoints by grounding referred objects and interpreting spatial relations and reference-frame cues. Evaluation of eleven generators reveals substantial room for improvement on MindView. A paired context analysis further shows that all eleven generators obtain lower overall scores under the expanded context setting. These findings motivate us to …
- Kategoria arxiv
- cs.CV
- Kategoria
- Widzenie komputerowe