Global-Local Face Upsampling Network
By Oncel Tuzel, Yuichi Taguchi, John R. Hershey. 2016
37 citations recorded by the source corpus.
Face hallucination, which is the task of generating a high-resolution face image from a low-resolution input image, is a well-studied problem that is useful in widespread application areas. Face hallucination is particularly challenging when the input face resolution is very low (e.g., 10 x 12 pixels) and/or the image is captured in an uncontrolled setting with large pose and illumination variations. In this paper, we revisit the algorithm introduced in [1] and present a deep interpretation of this framework that achieves state-of-the-art under such challenging scenarios. In our deep network architecture the global and local constraints that define a face can be efficiently modeled and learned end-to-end using training data. Conceptually our network design can be partitioned into two sub-networks: the first one implements the holistic face reconstruction according to global constraints, and the second one enhances face-specific details and enforces local patch statistics. We optimize the deep network using a new loss function for super-resolution that combines reconstruction error with a learned face quality measure in adversarial setting, producing improved visual results. We conduct extensive experiments in both controlled and uncontrolled setups and show that our algorithm improves the state of the art both numerically and visually.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Chunhua Shen
- Dacheng Tao
- Lei Zhang
- Xiaogang Wang
- Chen Change Loy
- Xiaoming Liu
Citations in the corpus
- Learning from Simulated and Unsupervised Images through Adversarial Training (2016, background): “[36] tackled image superresolution for face images with GANs.”
- FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors (2017, methodology): “We compare FSRNet with state-of-the-art SR methods, including generic SR methods like SRResNet [22], VDSR [17] and SRCNN [6]; and facial SR methods like GLN [35] and URDGN [42].”