AI RESEARCH
SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation
arXiv CS.CL
•
ArXi:2605.22536v1 Announce Type: cross Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pristine visual inputs and overlook the degradations that commonly occur in real-world deployment, such as motion blur, low light, adverse weather, lens distortion, and compression artifacts. This raises a fundamental question: how robust is the spatial intelligence of current MLLMs when visual observations are imperfect? To answer this question, we.