VGGHeads：用于3D人类头部的大规模合成数据集

VGGHeads: A Large-Scale Synthetic Dataset for 3D Human Heads

July 25, 2024

作者: Orest Kupyn, Eugene Khvedchenia, Christian Rupprecht

cs.AI

摘要

人头检测、关键点估计和3D头部模型拟合是许多应用中重要的任务。然而，传统的真实世界数据集通常存在偏见、隐私和伦理问题，并且是在实验室环境中记录的，这使得训练模型很难泛化。在这里，我们介绍VGGHeads -- 一个使用扩散模型生成的大规模合成数据集，用于人头检测和3D网格估计。我们的数据集包含超过100万张高分辨率图像，每张图像都标注有详细的3D头部网格、面部关键点和边界框。利用这个数据集，我们提出了一种新的模型架构，能够在单个步骤中从单个图像中同时检测头部并重建头部网格。通过广泛的实验评估，我们展示了在我们的合成数据上训练的模型在真实图像上取得了良好的性能。此外，我们的数据集的多功能性使其适用于广泛的任务，提供了对人头的一般和全面的表示。此外，我们提供了有关合成数据生成流程的详细信息，使其可以被重新用于其他任务和领域。

English

Human head detection, keypoint estimation, and 3D head model fitting are important tasks with many applications. However, traditional real-world datasets often suffer from bias, privacy, and ethical concerns, and they have been recorded in laboratory environments, which makes it difficult for trained models to generalize. Here, we introduce VGGHeads -- a large scale synthetic dataset generated with diffusion models for human head detection and 3D mesh estimation. Our dataset comprises over 1 million high-resolution images, each annotated with detailed 3D head meshes, facial landmarks, and bounding boxes. Using this dataset we introduce a new model architecture capable of simultaneous heads detection and head meshes reconstruction from a single image in a single step. Through extensive experimental evaluations, we demonstrate that models trained on our synthetic data achieve strong performance on real images. Furthermore, the versatility of our dataset makes it applicable across a broad spectrum of tasks, offering a general and comprehensive representation of human heads. Additionally, we provide detailed information about the synthetic data generation pipeline, enabling it to be re-used for other tasks and domains.