TL;DR本文提出了一种从大量非约束人脸图像中学习非线性 3D Morphable Model 的创新框架,该模型拥有比线性模型更强大的表示能力,并对人脸对齐和 3D 重建做出了贡献。
Abstract
As a classic statistical model of 3D facial shape and texture, 3D Morphable
Model (3DMM) is widely used in facial analysis, e.g., model fitting, image
synthesis. Conventional 3DMM is learned from a set of well-controlled 2D face
images with associated 3D face scans, and represented by