Deblurring Face Images Using Uncertainty Guided Multi-Stream Semantic Networks

@article{Yasarla2020DeblurringFI,
  title={Deblurring Face Images Using Uncertainty Guided Multi-Stream Semantic Networks},
  author={Rajeev Yasarla and Federico Perazzi and Vishal M. Patel},
  journal={IEEE Transactions on Image Processing},
  year={2020},
  volume={29},
  pages={6251-6263}
}
We propose a novel multi-stream architecture and training methodology that exploits semantic labels for facial image deblurring. The proposed Uncertainty Guided Multi-Stream Semantic Network (UMSN) processes regions belonging to each semantic class independently and learns to combine their outputs into the final deblurred result. Pixel-wise semantic labels are obtained using a segmentation network. A predicted confidence measure is used during training to guide the network towards the… 
Progressive Semantic Face Deblurring
TLDR
A multi-semantic progressive learning (MSPL) framework that progressively restores the entire face image starting from the facial components such as the skin, followed by the hair, and the inner parts (eyes, nose, and mouth).
FineNet: Frame Interpolation and Enhancement for Face Video Deblurring
TLDR
This work proposes a method that tackles the problem of deblur face videos from two directions: enhancing the blurry frames, and treating the blurryFrames as missing values and estimate them by interpolation, which outperforms the previous state-of-the-art methods by a large margin.
Face Deblurring Based on Separable Normalization and Adaptive Denormalization
  • Xian Zhang, Hao Zhang, Jiancheng Lv, Xiaojie Li
  • Computer Science
    ArXiv
  • 2021
TLDR
Experimental results demonstrate that the proposed face deblurring network restores face structure with more facial details and performs favorably against state-of-the-art methods in terms of structured similarity indexing method (SSIM), peak signal-to-noise ratio (PSNR), Frechet inception distance (FID) and L1, and qualitative comparisons.
Learning to Deblur and Rotate Motion-Blurred Faces
TLDR
A solution to the novel task of rendering sharp videos from new viewpoints from a single motion-blurred image of a face by implicitly learning the geometry and motion of faces through the joint training on three large datasets: FFHQ and 300VW, and a new Bern Multi-View Face Dataset (BMFD) that is built.
Network Architecture Search for Face Enhancement
TLDR
A multi-task face restoration network, called Network Architecture Search for Face Enhancement (NASFE), which can enhance poor quality face images containing a single degradation or multiple degradations, and introduces FFT-op and deveiling operators in the fusion network to efficiently fuse the task-specific features.
Balancing Heterogeneous Image Quality for Improved Cross-Spectral Face Recognition
TLDR
This paper studies the scenario where visible light faces are acquired at a short standoff, while IR faces are long-range data, and proposes a cascaded face enhancement structure that combines an existing denoising algorithm (BM3D) with a new deep-learning-based deblurring model (named SVDFace).
Face and Body-Based Human Recognition by GAN-Based Blur Restoration
TLDR
A recognition method is proposed wherein the blur of body and face images is restored using a generative adversarial network (GAN), and the features of face and body obtained using a deep convolutional neural network (CNN) are used to fuse the matching score.
Learning to Restore a Single Face Image Degraded by Atmospheric Turbulence using CNNs
TLDR
Comprehensive experiments on synthetic and real face images show that this framework is capable of alleviating blur and geometric distortion caused by atmospheric turbulence, and significantly improves the visual quality.
Deep Unfolding Network for Image Super-Resolution
  • K. Zhang, L. Gool, R. Timofte
  • Engineering, Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
TLDR
This paper proposes an end-to-end trainable unfolding network which leverages both learningbased methods and model-based methods to super-resolve blurry, noisy images for different scale factors via a single model, while maintaining the advantages of learning- based methods.
ATFaceGAN: Single Face Semantic Aware Image Restoration and Recognition From Atmospheric Turbulence
TLDR
A generative single frame restoration algorithm is proposed which disentangles the blur and deformation due to turbulence and reconstructs a restored image which achieves satisfactory performance for face restoration and face recognition tasks.
...
1
2
3
...

References

SHOWING 1-10 OF 56 REFERENCES
Deep Semantic Face Deblurring
TLDR
Quantitative and qualitative evaluations demonstrate that the proposed face deblurring algorithm restores sharp images with more facial details and performs favorably against state-of-the-art methods in terms of restoration quality, face recognition and execution speed.
Face Super-Resolution Guided by Facial Component Heatmaps
TLDR
This paper proposes a method that explicitly incorporates structural information of faces into the face super-resolution process by using a multi-task convolutional neural network (CNN) and achieves superior face hallucination results and outperforms the state-of-the-art.
Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement
TLDR
This paper proposes a facial component guided deep Convolutional Neural Network to restore a coarse face image, which is denoted as the base image where the facial component is automatically generated from the input face image.
Face Video Deblurring Using 3D Facial Priors
TLDR
A novel face video deblurring network capitalizing on 3D facial priors based on an encoder-decoder architecture and a 3D face reconstruction and rendering branch for predicting 3D priors of salient facial structures and identity knowledge is proposed.
Unsupervised Domain-Specific Deblurring via Disentangled Representations
TLDR
This paper presents an unsupervised method for domain-specific, single-image deblurring based on disentangled representations, and enforce a KL divergence loss to regularize the distribution range of extracted blur attributes such that little content information is contained.
Deep Learning Face Attributes in the Wild
TLDR
A novel deep learning framework for attribute prediction in the wild that cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently.
Gated Context Aggregation Network for Image Dehazing and Deraining
TLDR
An end-to-end gated context aggregation network to directly restore the final haze-free image by adopting the latest smoothed dilation technique to help remove the gridding artifacts caused by the widely-used dilated convolution with negligible extra parameters.
Deblurring Face Images with Exemplars
TLDR
A maximum a posteriori (MAP) deblurring algorithm based on an exemplar dataset, without using the coarse-to-fine strategy or ad-hoc edge selections is proposed, which addresses the problems ofdeblurring face images by exploiting facial structures.
Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
TLDR
This work proposes a multi-scale convolutional neural network that restores sharp images in an end-to-end manner where blur is caused by various sources and presents a new large-scale dataset that provides pairs of realistic blurry image and the corresponding ground truth sharp image that are obtained by a high-speed camera.
Super-FAN: Integrated Facial Landmark Localization and Super-Resolution of Real-World Low Resolution Faces in Arbitrary Poses with GANs
TLDR
The Super-FAN is proposed: the very first end-to-end system that addresses both tasks simultaneously, i.e. both improves face resolution and detects the facial landmarks.
...
1
2
3
4
5
...