AVGen-Bench：面向任务驱动的音视频生成多粒度评估基准

摘要

文本到音视频生成技术正迅速成为媒体创作的核心接口，但其评估体系仍处于碎片化状态。现有基准大多孤立评估音频与视频组件，或依赖粗糙的嵌入向量相似度，无法捕捉现实提示词所要求的细粒度联合准确性。我们推出AVGen-Bench——一个面向T2AV生成的任务驱动型基准测试，涵盖11个现实场景类别的高质量提示词。为支持全面评估，我们提出多粒度评估框架，将轻量级专家模型与多模态大语言模型相结合，实现从感知质量到细粒度语义可控性的全方位评估。研究结果表明，当前系统在强视听美学表现与弱语义可靠性之间存在显著断层，包括文本渲染失效、语音连贯性不足、物理推理错误等持续性问题，以及音乐音高控制的普遍失效。代码与基准资源详见http://aka.ms/avgenbench。

English

Text-to-Audio-Video (T2AV) generation is rapidly becoming a core interface for media creation, yet its evaluation remains fragmented. Existing benchmarks largely assess audio and video in isolation or rely on coarse embedding similarity, failing to capture the fine-grained joint correctness required by realistic prompts. We introduce AVGen-Bench, a task-driven benchmark for T2AV generation featuring high-quality prompts across 11 real-world categories. To support comprehensive assessment, we propose a multi-granular evaluation framework that combines lightweight specialist models with Multimodal Large Language Models (MLLMs), enabling evaluation from perceptual quality to fine-grained semantic controllability. Our evaluation reveals a pronounced gap between strong audio-visual aesthetics and weak semantic reliability, including persistent failures in text rendering, speech coherence, physical reasoning, and a universal breakdown in musical pitch control. Code and benchmark resources are available at http://aka.ms/avgenbench.

AVGen-Bench：面向任务驱动的音视频生成多粒度评估基准

AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation

摘要

Support