AI RESEARCH
360{\deg} Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method
arXiv CS.AI
•
ArXi:2603.16179v1 Announce Type: cross Multimodal Large Language Models (MLLMs) have shown impressive abilities in understanding and reasoning over conventional images. However, their perception of 360{\deg} images remains largely underexplored. Unlike conventional images, 360{\deg} images capture the entire surrounding environment, enabling holistic spatial reasoning but