Characteristic Regularisation for Super-Resolving Face Images
- URL: http://arxiv.org/abs/1912.12987v1
- Date: Mon, 30 Dec 2019 16:27:24 GMT
- Title: Characteristic Regularisation for Super-Resolving Face Images
- Authors: Zhiyi Cheng, Xiatian Zhu, Shaogang Gong
- Abstract summary: Existing facial image super-resolution (SR) methods focus mostly on improving artificially down-sampled low-resolution (LR) imagery.
Previous unsupervised domain adaptation (UDA) methods address this issue by training a model using unpaired genuine LR and HR data.
This renders the model overstretched with two tasks: consistifying the visual characteristics and enhancing the image resolution.
We formulate a method that joins the advantages of conventional SR and UDA models.
- Score: 81.84939112201377
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Existing facial image super-resolution (SR) methods focus mostly on improving
artificially down-sampled low-resolution (LR) imagery. Such SR models, although
strong at handling artificial LR images, often suffer from significant
performance drop on genuine LR test data. Previous unsupervised domain
adaptation (UDA) methods address this issue by training a model using unpaired
genuine LR and HR data as well as cycle consistency loss formulation. However,
this renders the model overstretched with two tasks: consistifying the visual
characteristics and enhancing the image resolution. Importantly, this makes the
end-to-end model training ineffective due to the difficulty of back-propagating
gradients through two concatenated CNNs. To solve this problem, we formulate a
method that joins the advantages of conventional SR and UDA models.
Specifically, we separate and control the optimisations for characteristics
consistifying and image super-resolving by introducing Characteristic
Regularisation (CR) between them. This task split makes the model training more
effective and computationally tractable. Extensive evaluations demonstrate the
performance superiority of our method over state-of-the-art SR and UDA models
on both genuine and artificial LR facial imagery data.
Related papers
- Efficient Test-Time Adaptation for Super-Resolution with Second-Order
Degradation and Reconstruction [62.955327005837475]
Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images.
We present an efficient test-time adaptation framework for SR, named SRTTA, which is able to quickly adapt SR models to test domains with different/unknown degradation types.
arXiv Detail & Related papers (2023-10-29T13:58:57Z) - Learning Many-to-Many Mapping for Unpaired Real-World Image
Super-resolution and Downscaling [60.80788144261183]
We propose an image downscaling and SR model dubbed as SDFlow, which simultaneously learns a bidirectional many-to-many mapping between real-world LR and HR images unsupervisedly.
Experimental results on real-world image SR datasets indicate that SDFlow can generate diverse realistic LR and SR images both quantitatively and qualitatively.
arXiv Detail & Related papers (2023-10-08T01:48:34Z) - ICF-SRSR: Invertible scale-Conditional Function for Self-Supervised
Real-world Single Image Super-Resolution [60.90817228730133]
Single image super-resolution (SISR) is a challenging problem that aims to up-sample a given low-resolution (LR) image to a high-resolution (HR) counterpart.
Recent approaches are trained on simulated LR images degraded by simplified down-sampling operators.
We propose a novel Invertible scale-Conditional Function (ICF) which can scale an input image and then restore the original input with different scale conditions.
arXiv Detail & Related papers (2023-07-24T12:42:45Z) - Real Image Super-Resolution using GAN through modeling of LR and HR
process [20.537597542144916]
We propose a learnable adaptive sinusoidal nonlinearities incorporated in LR and SR models by directly learn degradation distributions.
We demonstrate the effectiveness of our proposed approach in quantitative and qualitative experiments.
arXiv Detail & Related papers (2022-10-19T09:23:37Z) - SRDiff: Single Image Super-Resolution with Diffusion Probabilistic
Models [19.17571465274627]
Single image super-resolution (SISR) aims to reconstruct high-resolution (HR) images from the given low-resolution (LR) ones.
We propose a novel single image super-resolution diffusion probabilistic model (SRDiff)
SRDiff is optimized with a variant of the variational bound on the data likelihood and can provide diverse and realistic SR predictions.
arXiv Detail & Related papers (2021-04-30T12:31:25Z) - Real-World Super-Resolution of Face-Images from Surveillance Cameras [25.258587196435464]
We propose a novel framework for generation of realistic LR/HR training pairs.
Our framework estimates realistic blur kernels, noise distributions, and JPEG compression artifacts to generate LR images with similar image characteristics as the ones in the source domain.
For better perceptual quality we use a Generative Adrial Network (GAN) based SR model where we have exchanged the commonly used VGG-loss [24] with LPIPS-loss [52]
arXiv Detail & Related papers (2021-02-05T11:38:30Z) - Joint Generative Learning and Super-Resolution For Real-World
Camera-Screen Degradation [6.14297871633911]
In real-world single image super-resolution (SISR) task, the low-resolution image suffers more complicated degradations.
In this paper, we focus on the camera-screen degradation and build a real-world dataset (Cam-ScreenSR)
We propose a joint two-stage model. Firstly, the downsampling degradation GAN(DD-GAN) is trained to model the degradation and produces more various of LR images.
Then the dual residual channel attention network (DuRCAN) learns to recover the SR image.
arXiv Detail & Related papers (2020-08-01T07:10:13Z) - PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of
Generative Models [77.32079593577821]
PULSE (Photo Upsampling via Latent Space Exploration) generates high-resolution, realistic images at resolutions previously unseen in the literature.
Our method outperforms state-of-the-art methods in perceptual quality at higher resolutions and scale factors than previously possible.
arXiv Detail & Related papers (2020-03-08T16:44:31Z) - DDet: Dual-path Dynamic Enhancement Network for Real-World Image
Super-Resolution [69.2432352477966]
Real image super-resolution(Real-SR) focus on the relationship between real-world high-resolution(HR) and low-resolution(LR) image.
In this article, we propose a Dual-path Dynamic Enhancement Network(DDet) for Real-SR.
Unlike conventional methods which stack up massive convolutional blocks for feature representation, we introduce a content-aware framework to study non-inherently aligned image pair.
arXiv Detail & Related papers (2020-02-25T18:24:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.