SSMNBench: Diagnosing Image-based Cross-View Human-Object Understanding via Single-View Sufficiency and Multi-View Necessity
For researchers developing multimodal models, this benchmark provides a rigorous diagnostic tool to identify and address fundamental limitations in cross-view reasoning, which is critical for applications like surveillance and autonomous driving.
The paper introduces SSMNBench, a diagnostic benchmark with 3,300 QA pairs to evaluate cross-view human-object understanding in MLLMs. It reveals that models suffer from distraction degradation on redundant views and fail to integrate fragmented cross-view evidence, relying on single-image averaging rather than genuine cross-view synthesis.
Multimodal Large Language Models (MLLMs) have shown remarkable progress in single-image perception, yet their ability to reason about complex cross-view human-centric scenes remains largely unverified. Current multi-view benchmarks evaluate models using a fixed "bag of frames" and thus conflate a model's robustness to visual distraction with its genuine ability to fuse fragmented cross-view evidence. To address this issue, we introduce SSMNBench, a diagnostic benchmark comprising 3,300 curated QA pairs for cross-view human and human-object understanding. SSMNBench uniquely categorizes tasks into Single-View Sufficiency (SVS) and Multi-View Necessity (MVN). By systematically perturbing view availability across 17 state-of-the-art MLLMs, critical limitations are revealed: models suffer from severe "distraction degradation" when presented with redundant views (SVS), and fail to integrate fragmented geometric evidence across cameras (MVN). Our evaluations demonstrate that modern MLLMs rely on multiple single-image semantic averaging and view preference rather than genuine cross-view synthesis. By exposing these fundamental vulnerabilities, SSMNBench provides a rigorous diagnostic framework to drive the advancement of future cross-view-aware multimodal architectures. The code is available at: $ \href{https://github.com/gtc-gh/SSMNBench}{\text{SSMNBench}} $