Face Hallucination
12 papers with code • 1 benchmarks • 3 datasets
Face hallucination is the task of generating high-resolution (HR) facial images from low-resolution (LR) inputs.
( Image credit: Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination )
Benchmarks
These leaderboards are used to track progress in Face Hallucination
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
FFHQ
EDFace-Celeb-1M
KID-F
Most implemented papers
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
xinntao/ESRGAN
•
•
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).
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
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.
HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
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.
Context-Patch Face Hallucination Based on Thresholding Locality-constrained Representation and Reproducing Learning
junjun-jiang/Face-Hallucination-Benchmark
•
•
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).
DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-Resolution
andreas128/NTIRE21_Learning_SR_Space
•
•
To the best of our knowledge, DeepSEE is the first method to leverage semantic maps for explorative super-resolution.
Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination
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.
SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination
jesse1029/SiGAN
•
•
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.
Face Hallucination via Split-Attention in Split-Attention Network
mdswyz/SISN-Face-Hallucination
•
•
However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e. g., face detection, facial recognition).
Deep Learning-based Face Super-Resolution: A Survey
junjun-jiang/Face-Hallucination-Benchmark
•
•
Second, we elaborate on the facial characteristics and popular datasets used in FSR.
Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN
sam575/axial-gan
•
•
Existing thermal-to-visible face verification approaches expect the thermal and visible face images to be of similar resolution.
