Unsupervised Remote Sensing Super-Resolution via Migration Image Prior
- URL: http://arxiv.org/abs/2105.03579v1
- Date: Sat, 8 May 2021 03:29:35 GMT
- Title: Unsupervised Remote Sensing Super-Resolution via Migration Image Prior
- Authors: Jiaming Wang, Zhenfeng Shao, Tao Liu, Xiao Huang, Ruiqian Zhang, Yu
Wang
- Abstract summary: We propose a new unsupervised learning framework, called "MIP", which achieves super-resolution tasks without low/high resolution image pairs.
In this paper, we show that MIP achieves significant improvements over state-of-the-art methods both quantitatively and qualitatively.
- Score: 12.728430583409997
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recently, satellites with high temporal resolution have fostered wide
attention in various practical applications. Due to limitations of bandwidth
and hardware cost, however, the spatial resolution of such satellites is
considerably low, largely limiting their potentials in scenarios that require
spatially explicit information. To improve image resolution, numerous
approaches based on training low-high resolution pairs have been proposed to
address the super-resolution (SR) task. Despite their success, however,
low/high spatial resolution pairs are usually difficult to obtain in satellites
with a high temporal resolution, making such approaches in SR impractical to
use. In this paper, we proposed a new unsupervised learning framework, called
"MIP", which achieves SR tasks without low/high resolution image pairs. First,
random noise maps are fed into a designed generative adversarial network (GAN)
for reconstruction. Then, the proposed method converts the reference image to
latent space as the migration image prior. Finally, we update the input noise
via an implicit method, and further transfer the texture and structured
information from the reference image. Extensive experimental results on the
Draper dataset show that MIP achieves significant improvements over
state-of-the-art methods both quantitatively and qualitatively. The proposed
MIP is open-sourced at http://github.com/jiaming-wang/MIP.
Related papers
- SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models [3.839322642354617]
We propose a novel diffusion-based fusion algorithm called textbfSatDiffMoE.
Our algorithm is highly flexible and allows training and inference on arbitrary number of low-resolution images.
Experimental results show that our proposed SatDiffMoE method achieves superior performance for the satellite image super-resolution tasks.
arXiv Detail & Related papers (2024-06-14T17:58:28Z) - Learning Resolution-Adaptive Representations for Cross-Resolution Person
Re-Identification [49.57112924976762]
Cross-resolution person re-identification problem aims to match low-resolution (LR) query identity images against high resolution (HR) gallery images.
It is a challenging and practical problem since the query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras.
This paper explores an alternative SR-free paradigm to directly compare HR and LR images via a dynamic metric, which is adaptive to the resolution of a query image.
arXiv Detail & Related papers (2022-07-09T03:49:51Z) - Hierarchical Similarity Learning for Aliasing Suppression Image
Super-Resolution [64.15915577164894]
A hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing.
HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.
arXiv Detail & Related papers (2022-06-07T14:55:32Z) - Real-World Image Super-Resolution by Exclusionary Dual-Learning [98.36096041099906]
Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input.
Deep learning-based methods have achieved promising restoration quality on real-world image super-resolution datasets.
We propose Real-World image Super-Resolution by Exclusionary Dual-Learning (RWSR-EDL) to address the feature diversity in perceptual- and L1-based cooperative learning.
arXiv Detail & Related papers (2022-06-06T13:28:15Z) - SRR-Net: A Super-Resolution-Involved Reconstruction Method for High
Resolution MR Imaging [7.42807471627113]
The proposed SRR-Net is capable of recovering high-resolution brain images with both good visual quality and perceptual quality.
Experiment results using in-vivo HR multi-coil brain data indicate that the proposed SRR-Net is capable of recovering high-resolution brain images.
arXiv Detail & Related papers (2021-04-13T02:19:12Z) - A new public Alsat-2B dataset for single-image super-resolution [1.284647943889634]
The paper introduces a novel public remote sensing dataset (Alsat2B) of low and high spatial resolution images (10m and 2.5m respectively) for the single-image super-resolution task.
The high-resolution images are obtained through pan-sharpening.
The obtained results reveal that the proposed scheme is promising and highlight the challenges in the dataset.
arXiv Detail & Related papers (2021-03-21T10:47:38Z) - Deep Cyclic Generative Adversarial Residual Convolutional Networks for
Real Image Super-Resolution [20.537597542144916]
We consider a deep cyclic network structure to maintain the domain consistency between the LR and HR data distributions.
We propose the Super-Resolution Residual Cyclic Generative Adversarial Network (SRResCycGAN) by training with a generative adversarial network (GAN) framework for the LR to HR domain translation.
arXiv Detail & Related papers (2020-09-07T11:11:18Z) - Fusion of Deep and Non-Deep Methods for Fast Super-Resolution of
Satellite Images [54.44842669325082]
This work proposes to bridge the gap between image quality and the price by improving the image quality via super-resolution (SR)
We design an SR framework that analyzes the regional information content on each patch of the low-resolution image.
We show substantial decrease in inference time while achieving similar performance to that of existing deep SR methods.
arXiv Detail & Related papers (2020-08-03T13:55:39Z) - 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) - HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of
Satellite Imagery [55.253395881190436]
Multi-frame Super-Resolution (MFSR) offers a more grounded approach to the ill-posed problem.
This is important for satellite monitoring of human impact on the planet.
We present HighRes-net, the first deep learning approach to MFSR that learns its sub-tasks in an end-to-end fashion.
arXiv Detail & Related papers (2020-02-15T22:17:47Z)
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.