为设计类视频生成建立自动评估框架，解决动画结构与运动一致性难题。
Evaluating Design Video Generation: Metrics for Compositional Fidelity
- 构建四维自动化评估体系：布局、运动、时间、内容一致性
- 首次实现对设计动画中组件运动类型、方向、速度的精准量化
- 适合视频生成研究者与工业设计自动化工具开发者参考
生成式视频模型在设计动画任务中应用日益广泛，但该领域尚无标准化评估框架。与自然视频生成不同，设计动画具有严格结构约束：特定组件须按指定运动类型、方向、速度和时序变化，非动画区域必须保持稳定，整体布局结构需完整保留。本文提出一个全自动评估框架，涵盖布局保真度、运动正确性、时间质量与内容保真度四个维度，摆脱对主观人工评价的依赖，为该领域发展提供统一基准。代码与数据集已开源：https://github.com/purvanshi/lica-bench。
原文摘要 · Abstract (English)
Generative video models are increasingly used in design animation tasks, yet no standardized evaluation framework exists for this domain. Unlike natural video generation, design animation imposes structured constraints: specific components shall animate with prescribed motion types, directions, speed and timing, while non-animated regions must remain stable and layout structure must be preserved. This paper provides a fully automated evaluation framework organized across four dimensions: layout fidelity, motion correctness, temporal quality, and content fidelity. This eliminates the reliance on subjective human evaluation and establishes a common basis for benchmarking progress in the field. We release the code and dataset here: https://github.com/purvanshi/lica-bench.
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。