Face Hallucination Using Cascaded Super-Resolution and Identity Priors
| Autor: | Vitomir Struc, Walter J. Scheirer, Klemen Grm |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Face hallucination
Databases Factual Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Image processing 02 engineering and technology Facial recognition system Convolutional neural network Deep Learning Image Processing Computer-Assisted 0202 electrical engineering electronic engineering information engineering Humans Artificial neural network business.industry Deep learning Pattern recognition Computer Graphics and Computer-Aided Design Hallucinating Face Face (geometry) Identity (object-oriented programming) 020201 artificial intelligence & image processing Neural Networks Computer Artificial intelligence business Algorithms Software |
| Zdroj: | IEEE Transactions on Image Processing. 29:2150-2165 |
| ISSN: | 1941-0042 1057-7149 |
| Popis: | In this paper we address the problem of hallucinating high-resolution facial images from low-resolution inputs at high magnification factors. We approach this task with convolutional neural networks (CNNs) and propose a novel (deep) face hallucination model that incorporates identity priors into the learning procedure. The model consists of two main parts: i) a cascaded super-resolution network that upscales the low-resolution facial images, and ii) an ensemble of face recognition models that act as identity priors for the super-resolution network during training. Different from most competing super-resolution techniques that rely on a single model for upscaling (even with large magnification factors), our network uses a cascade of multiple SR models that progressively upscale the low-resolution images using steps of $2\times $ . This characteristic allows us to apply supervision signals (target appearances) at different resolutions and incorporate identity constraints at multiple-scales. The proposed C-SRIP model (Cascaded Super Resolution with Identity Priors) is able to upscale (tiny) low-resolution images captured in unconstrained conditions and produce visually convincing results for diverse low-resolution inputs. We rigorously evaluate the proposed model on the Labeled Faces in the Wild (LFW), Helen and CelebA datasets and report superior performance compared to the existing state-of-the-art. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|