360deg Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method

Multimodal Large Language Models (MLLMs) have shown impressive abilities in understanding and reasoning over conventional images. However, their perception of 360deg images remains largely underexplored. Unlike conventional images, 360deg images capture the entire surrounding environment, enabling holistic spatial reasoning but introducing challenges such as geometric distortion and complex spatial relations. To comprehensively assess MLLMs' capabilities to perceive 360deg images, we introduce 360Bench, a Visual Question Answering (VQA) benchmark featuring 7K-resolution 360deg images, seven representative (sub)tasks with annotations carefully curated by human annotators. Using 360Bench, we systematically evaluate seven MLLMs and six enhancement methods, revealing their shortcomings in 360deg image perception. To address these challenges, we propose Free360, a training-free scene-graph-based framework for high-resolution 360deg VQA. Free360 decomposes the reasoning process into modular steps, applies adaptive spherical image transformations to 360deg images tailored to each step, and seamlessly integrates the resulting information into a unified graph representation for answer generation. Experiments show that Free360 consistently improves its base MLLM and provides a strong training-free solution for 360deg VQA tasks. The source code and dataset will be publicly released upon acceptance.