10 papers with code • 1 benchmarks • 1 datasets
Face hallucination is the task of generating high-resolution (HR) facial images from low-resolution (LR) inputs.
To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN).
Ranked #2 on Face Hallucination on FFHQ 512 x 512 - 16x upscaling
We present an algorithm addressing this problem, PULSE (Photo Upsampling via Latent Space Exploration), which generates high-resolution, realistic images at resolutions previously unseen in the literature.
Ranked #9 on Image Super-Resolution on FFHQ 256 x 256 - 4x upscaling (SSIM metric)
Recent deep learning based face recognition methods have achieved great performance, but it still remains challenging to recognize very low-resolution query face like 28x28 pixels when CCTV camera is far from the captured subject.
Existing face restoration researches typically relies on either the degradation prior or explicit guidance labels for training, which often results in limited generalization ability over real-world images with heterogeneous degradations and rich background contents.
To the best of our knowledge, DeepSEE is the first method to leverage semantic maps for explorative super-resolution.
To this end, this study incorporates the contextual information of image patch and proposes a powerful and efficient context-patch based face hallucination approach, namely Thresholding Locality-constrained Representation and Reproducing learning (TLcR-RL).
Despite generative adversarial networks (GANs) can hallucinate photo-realistic high-resolution (HR) faces from low-resolution (LR) faces, they cannot guarantee preserving the identities of hallucinated HR faces, making the HR faces poorly recognizable.
Existing thermal-to-visible face verification approaches expect the thermal and visible face images to be of similar resolution.
Most of the current face hallucination methods, whether they are shallow learning-based or deep learning-based, all try to learn a relationship model between Low-Resolution (LR) and High-Resolution (HR) spaces with the help of a training set.