从遮挡人脸图像中重建带细节的3D面部模型
3D Face Reconstruction With Geometry Details From a Single Color Image Under Occluded Scenes
- 结合凹凸贴图，增强粗略3D人脸的中等层级细节
- 可同时处理头发、手掌、眼镜等多种遮挡情况
- 适合需要高精度3D人脸重建的应用场景
3D人脸重建技术旨在生成自然真实的面部立体模型。以往基于深度学习的方法通常侧重于生成逼真的纹理，但在多种遮挡场景下泛化能力较差。本文引入凹凸贴图（bump mapping），成功为粗略3D人脸添加了中等层次的几何细节。更创新的是，该方法考虑了遮挡情形，提出一个统一框架，能同时处理多种遮挡类型（如头发、手掌、眼镜等）。大量实验与对比表明，该方法可在遮挡场景下，从捕获的人脸图像中生成高质量且带有几何细节的重建结果。
原文摘要 · Abstract (English)
3D face reconstruction technology aims to generate a face stereo model naturally and realistically. Previous deep face reconstruction approaches are typically designed to generate convincing textures and cannot generalize well to multiple occluded scenarios simultaneously. By introducing bump mapping, we successfully added mid-level details to coarse 3D faces. More innovatively, our method takes into account occlusion scenarios. Thus on top of common 3D face reconstruction approaches, we in this paper propose a unified framework to handle multiple types of obstruction simultaneously (e.g., hair, palms and glasses et al.).Extensive experiments and comparisons demonstrate that our method can generate high-quality reconstruction results with geometry details from captured facial images under occluded scenes.
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。