Title: Plenoptic Face Analysis
Abstract:
Face analysis is one of essential research topics in the fields of machine learning and computer vision. It has a wide range of applications in smart phones, financial payment, public security, interactive entertainment, etc. By editing, synthesizing and generating new face images, not only the quality of the original face image could be improved, but also the large-scale face data could be augmented to improve the robustness of modern face recognition system for complicated environments.
Plenoptic face analysis contains the collection, reconstruction, edition, interpretation and recognition of visual face images. The research content is roughly divided into theory and application. The theoretical research covers image acquisition, deep learning, transfer learning, weakly-supervised learning etc., while the application research involves face alignment, face rotation, expression synthesis, attribute edition, etc. Based on visual information acquisition and deep learning framework, this tutorial deeply analyzes the theory and application of plenoptic face analysis. First, the basic part will introduce the main theories and methods involved in deep plenoptic face analysis from the respects of plenoptic computational photography, visual topology cognition, probabilistic generative models and identity preserving structures. Then, the application part will dive into the specific application scenarios and the recent developments of face generation, face rotation, age synthesis, light field imaging and so on. The related researches were published in several top journals and conferences, such as IJCV, IEEE TPAMI, TIP, TIFS, ICCV, CVPR, ECCV, NeurIPS, AAAI.
References:
[1] Ran He, Xiang Wu, Zhenan Sun, Tieniu Tan. Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition. IEEE Trans. Pattern Analysis and Machine Intelligence, 2018, 10.1109/TPAMI.2018.2842770.
[2] Xiang Wu, Ran He, Zhenan Sun, Tieniu Tan. A Light CNN for Deep Face Representation with Noisy Labels. IEEE Trans. Information Forensics and Security (2018).
[3] Jie Cao, Yibo Hu, Bing Yu, Ran He, Zhenan Sun. 3D Aided Duet GANs for Multi-view Face Image Synthesis. IEEE Trans. Information Forensics and Security (2019).
[4] Peipei Li, Yibo Hu, Ran He, Zhenan Sun. Global and Local Consistent Wavelet-domain Age Synthesis. IEEE Trans. Information Forensics and Security (2019).
[5] Rui Huang, Shu Zhang, Tianyu Li, Ran He. Beyond face rotation: Global and local perception GAN for photorealistic and identity preserving frontal view synthesis. ICCV 2017.
[6] Yunlong Wang, Fei Liu, Zilei Wang, Guangqi Hou, Zhenan Sun, Tieniu Tan. End-to-end View Synthesis for Light Field Imaging with Pseudo 4DCNN. ECCV, 2018.
[7] Yibo Hu, Xiang Wu, Bing Yu, Ran He and Zhenan Sun. Pose-Guided Photorealistic Face Rotation. CVPR 2018.
[8] Yi Li, Lingxiao Song, Xiang Wu, Ran He, Tieniu Tan. Anti-Makeup: Learning A Bi-Level Adversarial Network for Makeup-Invariant Face Verification. AAAI 2018.
[9] Lingxiao Song, Man Zhang, Xiang Wu, Ran He. Adversarial Discriminative Heterogeneous Face Recognition, AAAI 2018.
[10] Lingxiao Song, Zhihe Lu, Ran He, Zhenan Sun, Tieniu Tan. Geometry Guided Adversarial Facial Expression Synthesis. ACMMM, 2018.
[11] Huaibo Huang, Zhihang Li, Ran He, Zhenan Sun, Tieniu Tan. IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis. NeurIPS, 2018.
[12] Jie Cao, Yibo Hu, Hongwen Zhang, Ran He, Zhenan Sun. Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization. NeurIPS, 2018.
[13] Linsen Song, Jie Cao, Lingxiao Song, Yibo Hu, Ran He. Geometry-aware Face Completion and Editing. AAAI, 2019.
[14] International Journal of Computer Vision Special Issue on Deep Learning for Face Analysis.
Speakers:
 |
Ran He received the B.E. degree in Computer Science from Dalian University of Technology, the M.S. degree in Computer Science
from Dalian University of Technology, and Ph.D. degree in Pattern Recognition and Intelligent Systems from Institute of Automation, Chinese Academy of Sciences in 2001, 2004 and 2009, respectively. Since September 2010, Dr. He has joined NLPR where he is currently Professor. He currently serves as an associate editor of Neurocomputing (Elsevier) and serves on the program committee of several conferences. His research interests focus on information theoretic learning, pattern recognition, and computer vision. In recent years, he has published more than 130 papers in peer-reviewed journals and conferences, including IJCV, IEEE TPAMI, TNNLS, TIP, TIFS, CVPR, ICCV, NIPS, IJCAI, AAAI. His research is supported by Beijing Outstanding Youth Science Fund and National Natural Science Foundation of China Youth Fund. |
 |
Yunlong Wang is currently an assistant professor in CRIPAC, NLPR, CASIA, China. He received the B.E. degree and the Ph.D. degree in Department of Automation, University of Science and Technology of China. His research focuses on pattern recognition, machine learning, light field photography, and biometrics. He has published several papers in TIP/TCI/ECCV, et cetera. |
 |
Huaibo Huang is currently an assistant professor in CRIPAC, NLPR, CASIA, China. He received the B.E. degree in Measurement and Control Technology and Instrument from Xi’an Jiaotong University in 2012, the M.E. degree in Optical Engineering from Beihang University in 2016, the the Ph.D. degree in Pattern Recognition and Intelligent System from CASIA in 2019. His current research interests include computer vision and pattern recognition. He has published a book titled ‘Heterogeneous Facial Analysis and Synthesis’ and has published several papers in IJCV/ICCV/NIPS/AAAI. |
 |
Yibo Hu received the B.E. degree in Software Engineering from Dalian University of Technology in 2015, the M.S. degree in Pattern Recognition and Intelligent System from Institute of Automation, Chinese Academy of Sciences (CASIA) in 2018. He is a research assistant in Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), CASIA. His research interest focuses on deep learning and computer vision. He has rich practical experience in the fields of face rotation, facial age synthesis and estimation. He has published several papers in TIFS, CVPR, NIPS, AAAI. |