3D Face
3D face modeling focuses on creating and manipulating realistic three-dimensional representations of human faces, primarily for applications in computer vision, graphics, and medicine. Current research emphasizes developing robust and efficient methods for 3D face reconstruction from various input modalities (e.g., images, sketches, scans), often employing deep learning architectures like GANs, diffusion models, and neural radiance fields (NeRFs), along with parametric models such as 3DMMs. These advancements enable precise control over facial attributes (identity, expression, age, lighting), facilitating applications ranging from forensic facial reconstruction and personalized avatar creation to the development of more sophisticated facial recognition systems and the analysis of facial dysmorphologies.
Papers
3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs
Yanda Meng, Xu Chen, Dongxu Gao, Yitian Zhao, Xiaoyun Yang, Yihong Qiao, Xiaowei Huang, Yalin Zheng
Controllable Evaluation and Generation of Physical Adversarial Patch on Face Recognition
Xiao Yang, Yinpeng Dong, Tianyu Pang, Zihao Xiao, Hang Su, Jun Zhu