Real-World Super-Resolution of Face-Images from Surveillance Cameras
- URL: http://arxiv.org/abs/2102.03113v1
- Date: Fri, 5 Feb 2021 11:38:30 GMT
- Title: Real-World Super-Resolution of Face-Images from Surveillance Cameras
- Authors: Andreas Aakerberg, Kamal Nasrollahi, Thomas B. Moeslund
- Abstract summary: 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]
- Score: 25.258587196435464
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Most existing face image Super-Resolution (SR) methods assume that the
Low-Resolution (LR) images were artificially downsampled from High-Resolution
(HR) images with bicubic interpolation. This operation changes the natural
image characteristics and reduces noise. Hence, SR methods trained on such data
most often fail to produce good results when applied to real LR images. To
solve this problem, 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. This allows us
to train a SR model using high quality face images as Ground-Truth (GT). For
better perceptual quality we use a Generative Adversarial Network (GAN) based
SR model where we have exchanged the commonly used VGG-loss [24] with
LPIPS-loss [52]. Experimental results on both real and artificially corrupted
face images show that our method results in more detailed reconstructions with
less noise compared to existing State-of-the-Art (SoTA) methods. In addition,
we show that the traditional non-reference Image Quality Assessment (IQA)
methods fail to capture this improvement and demonstrate that the more recent
NIMA metric [16] correlates better with human perception via Mean Opinion Rank
(MOR).
Related papers
- ClearSR: Latent Low-Resolution Image Embeddings Help Diffusion-Based Real-World Super Resolution Models See Clearer [68.72454974431749]
We present ClearSR, a new method that can better take advantage of latent low-resolution image (LR) embeddings for diffusion-based real-world image super-resolution (Real-ISR)
Our model can achieve better performance across multiple metrics on several test sets and generate more consistent SR results with LR images than existing methods.
arXiv Detail & Related papers (2024-10-18T08:35:57Z) - 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) - 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) - Toward Real-world Image Super-resolution via Hardware-based Adaptive
Degradation Models [3.9037347042028254]
Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs.
We propose a novel supervised method to simulate an unknown degradation process with the inclusion of prior hardware knowledge.
Experiments on the real-world datasets validate that our degradation model can estimate LR images more accurately than the predetermined degradation operation.
arXiv Detail & Related papers (2021-10-20T19:53:48Z) - Hierarchical Conditional Flow: A Unified Framework for Image
Super-Resolution and Image Rescaling [139.25215100378284]
We propose a hierarchical conditional flow (HCFlow) as a unified framework for image SR and image rescaling.
HCFlow learns a mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously.
To further enhance the performance, other losses such as perceptual loss and GAN loss are combined with the commonly used negative log-likelihood loss in training.
arXiv Detail & Related papers (2021-08-11T16:11:01Z) - Frequency Consistent Adaptation for Real World Super Resolution [64.91914552787668]
We propose a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying Super-Resolution (SR) methods to the real scene.
We estimate degradation kernels from unsupervised images and generate the corresponding Low-Resolution (LR) images.
Based on the domain-consistent LR-HR pairs, we train easy-implemented Convolutional Neural Network (CNN) SR models.
arXiv Detail & Related papers (2020-12-18T08:25:39Z) - Benefiting from Bicubically Down-Sampled Images for Learning Real-World
Image Super-Resolution [22.339751911637077]
We propose to handle real-world SR by splitting this ill-posed problem into two comparatively more well-posed steps.
First, we train a network to transform real LR images to the space of bicubically downsampled images in a supervised manner.
Second, we take a generic SR network trained on bicubically downsampled images to super-resolve the transformed LR image.
arXiv Detail & Related papers (2020-07-06T20:27:58Z) - 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) - Characteristic Regularisation for Super-Resolving Face Images [81.84939112201377]
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.
arXiv Detail & Related papers (2019-12-30T16:27:24Z)
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.