Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization

Authors: Jie Cao, Yibo Hu, Hongwen Zhang, Ran He, Zhenan Sun

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Exhaustive experiments on both controlled and uncontrolled environments demonstrate that the proposed method not only boosts the performance of pose-invariant face recognition but also dramatically improves high-resolution frontalization appearances.
Researcher Affiliation Academia Jie Cao, Yibo Hu, Hongwen Zhang, Ran He , Zhenan Sun National Laboratory of Pattern Recognition, CASIA Center for Research on Intelligent Perception and Computing, CASIA Center for Excellence in Brain Science and Intelligence Technology, CASIA University of Chinese Academy of Sciences, Beijing, 100049, China {jie.cao,yibo.hu,hongwen.zhang}@cripac.ia.ac.cn {rhe,znsun}@nlpr.ia.ac.cn
Pseudocode Yes Algorithm 1 Training algorithm of HF-PIM
Open Source Code No The paper does not provide any links to open-source code or explicitly state that the code for the described methodology is released.
Open Datasets Yes To demonstrate the superiority of our method in both controlled and unconstrained environments and produce high-resolution face frontalization results, we conduct our experiment on four datasets: Multi-PIE [11], LFW [18], IJB-A [23], and Celeb A-HQ [22].
Dataset Splits Yes The training set is drawn from Multi-PIE and Celeb A-HQ. We follow the protocol in [33] to split the Multi-PIE dataset. The first 200 subjects are used for training and the rest 137 ones for testing. Each testing identity has one gallery image from his/her first appearance. Hence, there are 72,000 and 137 images in the probe and gallery sets, respectively. For Celeb A-HQ, we apply head pose estimation [41] to find those frontal faces and employ them (19, 203 images) for training. We choose those images with large poses (5, 998 ones) for testing.
Hardware Specification Yes Two NVIDIA Titan X GPUs with 12GB GDDR5X RAM is employed for the training and testing process.
Software Dependencies No Our proposed method is implemented based on the deep learning library Pytorch [27]. While Pytorch is mentioned, no specific version number for it or any other software dependency is provided.
Experiment Setup Yes We use Adam optimizer with a learning rate of 1e-4 and β1 = 0.5, β2 = 0.99.