GNC: Geometry Normal Consistency Loss for 3D Face Reconstruction and Dense Alignment

作者：Xing Zheng, Yongrong Cao, Lei Li, Zhiyuan Zhou, Meining Jia, Suping Wu · 发表于：2022 IEEE International Conference on Multimedia and Expo (ICME) · 年份：2022 · DOI：10.1109/icme52920.2022.9859696 · 被引用次数：3 · 研究领域：Face recognition and analysis、3D Shape Modeling and Analysis、Facial Rejuvenation and Surgery Techniques

In this work, we propose Geometry Normal Consistency Loss (GNC) for 3D face reconstruction and dense alignment. The existing methods based on the strong constraints of the 3DMM parameter regression only consider reducing the error between 68 landmarks, while they rarely consider the geometric contour structure relation of the face. Instead, we take into account the discrete 68 landmarks as loss constrain by introducing geometry area and normal consistency loss, which naturally defines the holistic and local geometric contour structure of the face. In detail, we select the inverted triangle formed by the leftmost and rightmost landmarks on the cheek and the lowest point of the chin to globally constrain the entire facial feature. In addition, we triangulate the facial landmarks to construct triangular patches, and calculate the normals of the patches, which aims to make use of normal consistency between the local patch and the corresponding ground truth to reconstruct rich local details. Extensive experimental results on AFLW2000-3D and AFLW datasets demonstrate that our GNC achieves compelling performance compared to the state of the arts.