提出细粒度人体视频评估框架，更贴近人眼判断标准。
HuM-Eval: A Coarse-to-Fine Framework for Human-Centric Video Evaluation
- 分粗到细两阶段评估：先看整体画面，再检人体姿态与运动稳定性。
- 在1000个提示上测试，平均人评相关性达58.2%，优于现有方法。
- 适合研究视频生成、人体动作建模的学者和开发者使用。
近年来视频生成模型快速发展，其中自然人体动作生成至关重要。然而，准确评估生成人体动作视频的质量仍面临挑战。现有评估指标多关注全局场景统计特征，忽略细粒度人体细节，导致与人类主观偏好不一致。为此，我们提出HuM-Eval，一种新型以人为中心的评估框架，采用粗到细策略：首先利用视觉语言模型进行全局视频质量粗评；随后通过2D姿态验证解剖结构正确性，3D人体运动评估动作稳定性。大量实验表明，HuM-Eval平均人评相关性达58.2%，超越现有最优基线。此外，我们构建了涵盖1000个多样化提示的HuM-Bench基准，对现有文本到视频模型进行详细评估，为下一代人体动作生成提供支持。
原文摘要 · Abstract (English)
Video generation models have developed rapidly in recent years, where generating natural human motion plays a pivotal role. However, accurately evaluating the quality of generated human motion video remains a significant challenge. Existing evaluation metrics primarily focus on global scene statistics, often overlooking fine-grained human details and consequently failing to align with human subjective preference. To bridge this gap, we propose HuM-Eval, a novel human-centric evaluation framework that adopts a coarse-to-fine strategy. Specifically, our framework first utilizes a Vision Language Model to perform a coarse assessment of global video quality. It then proceeds to a fine-grained analysis, using 2D pose to verify anatomical correctness and 3D human motion to evaluate motion stability. Extensive experiments demonstrate that HuM-Eval achieves an average human correlation of 58.2%, outperforming state-of-the-art baselines. Furthermore, we introduce HuM-Bench, a comprehensive benchmark comprising 1,000 diverse prompts, and conduct a detailed evaluation of existing text-to-video models, paving the way for next-generation human motion generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。