NJU-LINK/T2AV-Compass

T2AV-Compass是一个统一的基准测试，用于评估文本到音频视频（T2AV）生成，不仅针对单模态质量（视频/音频），还包括跨模态对齐与同步、复杂指令跟随以及基于物理/常识约束的感知真实性。该数据集包含500个分类驱动的提示和细粒度检查表，用于MLLM-as-a-Judge协议。

T2AV-Compass is a unified benchmark for evaluating Text-to-Audio-Video (T2AV) generation, targeting not only unimodal quality (video/audio) but also cross-modal alignment & synchronization, complex instruction following, and perceptual realism grounded in physical/common-sense constraints. This dataset includes 500 taxonomy-driven prompts and fine-grained checklists for an MLLM-as-a-Judge protocol.