VGA-Bench：视频美学与生成质量评估的统一基准与多模型框架
VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation
做视频生成的人可以直接用 VGA-Bench 的三层分类体系（美学质量、美学标签、生成质量）和三个多任务评估器（VAQA-Net、VTag-Net、VGQA-Net）作为自动化评测代理，替代昂贵的人工打分，用于模型选型、调试与生成质量监控。
原文依据 we introduce VGA-Bench, a unified benchmark for joint evaluation of video generation quality and aesthetic quality
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于 AIGC 的视频生成技术快速发展，凸显出对综合评估框架的迫切需求——这类框架需超越传统的生成质量指标，将美学吸引力纳入考量。然而，现有基准仍主要聚焦于技术保真度，在整体性评估方面存在明显空白，尤其是在感知与艺术品质层面。为弥补这一局限，我们提出 VGA-Bench，一个用于联合评估视频生成质量与美学质量的统一基准。VGA-Bench 建立在一个有原则的三层分类体系之上：美学质量、美学标签与生成质量，每一层又分解为多个细粒度子维度，以支持系统化评估。在该分类体系的指导下，我们设计了 1,016 条多样化提示词，并使用 12 个视频生成模型生成了包含 60,000 余条视频的大规模数据集，确保在内容、风格与伪影方面具有广泛覆盖。为实现可扩展的自动化评估，我们通过人工标注对数据集的一个子集进行标注，并开发了三个专用的多任务神经评估器：用于美学质量预测的 VAQA-Net、用于自动美学标签的 VTag-Net，以及用于生成质量与基础质量属性的 VGQA-Net。大量实验表明，我们的模型与人类判断实现了可靠的对齐，兼具准确性与效率。我们将 VGA-Bench 作为公开基准发布，以促进 AIGC 评估研究，其应用涵盖内容审核、模型调试与生成模型优化。
英文原文摘要 1578 字符
The rapid advancement of AIGC-based video generation has underscored the critical need for comprehensive evaluation frameworks that go beyond traditional generation quality metrics to encompass aesthetic appeal. However, existing benchmarks remain largely focused on technical fidelity, leaving a significant gap in holistic assessment--particularly with respect to perceptual and artistic qualities. To address this limitation, we introduce VGA-Bench, a unified benchmark for joint evaluation of video generation quality and aesthetic quality. VGA-Bench is built upon a principled three-tier taxonomy: Aesthetic Quality, Aesthetic Tagging, and Generation Quality, each decomposed into multiple fine-grained sub-dimensions to enable systematic assessment. Guided by this taxonomy, we design 1,016 diverse prompts and generate a large-scale dataset of over 60,000 videos using 12 video generation models, ensuring broad coverage across content, style, and artifacts. To enable scalable and automated evaluation, we annotate a subset of the dataset via human labeling and develop three dedicated multi-task neural assessors: VAQA-Net for aesthetic quality prediction, VTag-Net for automatic aesthetic tagging, and VGQA-Net for generation and basic quality attributes. Extensive experiments demonstrate that our models achieve reliable alignment with human judgments, offering both accuracy and efficiency. We release VGA-Bench as a public benchmark to foster research in AIGC evaluation, with applications in content moderation, model debugging, and generative model optimization.