构建首个全身数字人生成评估基准，支持真实对话动画生成。
Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos
- 提出多模态标注的全身数字人基准数据集
- 包含精细动作与表情标注，支持全身体态生成评估
- 开源数据与工具，适合虚拟人与动画研究者使用
从单张肖像生成逼真可动画的全身数字人极具挑战，受限于微表情、身体动作和动态背景的捕捉能力。现有评估数据集与指标难以应对这些复杂性。为此，我们提出全身体态数字人基准数据集（WB-DH），一个开源、多模态的评估基准，用于衡量全身可动画数字人生成效果。其核心特点包括：（1）提供细粒度的多模态标注以实现精准引导；（2）具备灵活的评估框架；（3）数据集与工具已公开，可通过 https://github.com/deepreasonings/WholeBodyBenchmark 获取。
原文摘要 · Abstract (English)
Creating realistic, fully animatable whole-body avatars from a single portrait is challenging due to limitations in capturing subtle expressions, body movements, and dynamic backgrounds. Current evaluation datasets and metrics fall short in addressing these complexities. To bridge this gap, we introduce the Whole-Body Benchmark Dataset (WB-DH), an open-source, multi-modal benchmark designed for evaluating whole-body animatable avatar generation. Key features include: (1) detailed multi-modal annotations for fine-grained guidance, (2) a versatile evaluation framework, and (3) public access to the dataset and tools at https://github.com/deepreasonings/WholeBodyBenchmark.
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。