Kernel Agnostic Real-world Image Super-resolution
- URL: http://arxiv.org/abs/2104.09008v1
- Date: Mon, 19 Apr 2021 01:51:21 GMT
- Title: Kernel Agnostic Real-world Image Super-resolution
- Authors: Hu Wang, Congbo Ma, Chunhua Shen
- Abstract summary: We introduce a new kernel agnostic SR framework to deal with real-world image SR problem.
In the proposed framework, the degradation kernels and noises are adaptively modeled rather than explicitly specified.
The experiments validate the effectiveness of the proposed framework on multiple real-world datasets.
- Score: 82.3963188538938
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, deep neural network models have achieved impressive results in
various research fields. Come with it, an increasing number of attentions have
been attracted by deep super-resolution (SR) approaches. Many existing methods
attempt to restore high-resolution images from directly down-sampled
low-resolution images or with the assumption of Gaussian degradation kernels
with additive noises for their simplicities. However, in real-world scenarios,
highly complex kernels and non-additive noises may be involved, even though the
distorted images are visually similar to the clear ones. Existing SR models are
facing difficulties to deal with real-world images under such circumstances. In
this paper, we introduce a new kernel agnostic SR framework to deal with
real-world image SR problem. The framework can be hanged seamlessly to multiple
mainstream models. In the proposed framework, the degradation kernels and
noises are adaptively modeled rather than explicitly specified. Moreover, we
also propose an iterative supervision process and frequency-attended objective
from orthogonal perspectives to further boost the performance. The experiments
validate the effectiveness of the proposed framework on multiple real-world
datasets.
Related papers
- Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation [3.2157163136267934]
We propose IKR-Net (Iterative Kernel Reconstruction Network) for blind SISR.
IKR-Net achieves state-of-the-art results in blind SISR, especially for noisy images with motion blur.
arXiv Detail & Related papers (2024-04-25T12:27:22Z) - ACDMSR: Accelerated Conditional Diffusion Models for Single Image
Super-Resolution [84.73658185158222]
We propose a diffusion model-based super-resolution method called ACDMSR.
Our method adapts the standard diffusion model to perform super-resolution through a deterministic iterative denoising process.
Our approach generates more visually realistic counterparts for low-resolution images, emphasizing its effectiveness in practical scenarios.
arXiv Detail & Related papers (2023-07-03T06:49:04Z) - RBSR: Efficient and Flexible Recurrent Network for Burst
Super-Resolution [57.98314517861539]
Burst super-resolution (BurstSR) aims at reconstructing a high-resolution (HR) image from a sequence of low-resolution (LR) and noisy images.
In this paper, we suggest fusing cues frame-by-frame with an efficient and flexible recurrent network.
arXiv Detail & Related papers (2023-06-30T12:14:13Z) - Single Image Internal Distribution Measurement Using Non-Local
Variational Autoencoder [11.985083962982909]
This paper proposes a novel image-specific solution, namely non-local variational autoencoder (textttNLVAE)
textttNLVAE is introduced as a self-supervised strategy that reconstructs high-resolution images using disentangled information from the non-local neighbourhood.
Experimental results from seven benchmark datasets demonstrate the effectiveness of the textttNLVAE model.
arXiv Detail & Related papers (2022-04-02T18:43:55Z) - Kernel-aware Raw Burst Blind Super-Resolution [0.0]
Burst super-resolution (SR) provides a possibility of restoring rich details from low-quality images.
Existing non-blind networks usually lead to a severe performance drop in recovering high-resolution (HR) images.
We introduce a kernel-aware deformable alignment module which can effectively align the raw images with consideration of the blurry priors.
arXiv Detail & Related papers (2021-12-14T11:49:13Z) - Unsupervised Single Image Super-resolution Under Complex Noise [60.566471567837574]
This paper proposes a model-based unsupervised SISR method to deal with the general SISR task with unknown degradations.
The proposed method can evidently surpass the current state of the art (SotA) method (about 1dB PSNR) not only with a slighter model (0.34M vs. 2.40M) but also faster speed.
arXiv Detail & Related papers (2021-07-02T11:55:40Z) - High-Frequency aware Perceptual Image Enhancement [0.08460698440162888]
We introduce a novel deep neural network suitable for multi-scale analysis and propose efficient model-agnostic methods.
Our model can be applied to multi-scale image enhancement problems including denoising, deblurring and single image super-resolution.
arXiv Detail & Related papers (2021-05-25T07:33:14Z) - Designing a Practical Degradation Model for Deep Blind Image
Super-Resolution [134.9023380383406]
Single image super-resolution (SISR) methods would not perform well if the assumed degradation model deviates from those in real images.
This paper proposes to design a more complex but practical degradation model that consists of randomly shuffled blur, downsampling and noise degradations.
arXiv Detail & Related papers (2021-03-25T17:40:53Z) - 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)
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.