Kernel Modeling Super-Resolution on Real Low-Resolution Images

Zhou, Ruofan; Süsstrunk, Sabine

doi:10.1109/iccv.2019.00252

Cited by 159 publications

(106 citation statements)

References 47 publications

Supporting

Mentioning

106

Contrasting

Order By: Relevance

“…Most super resolution models which estimate the true kernel involve complex optimization procedures [64][65][66][67][68][69]. Deep learning is an alternative strategy for estimating the true kernel for real-world image super resolution [70][71][72]. Deep learning-based models assume that the degradation kernels are not available and attempt to estimate the optimal kernel, either using self-similarity properties [64,70,71] or adapting an alternating optimization algorithm [63,73].…”

Section: Deep Learning-based Super Resolutionmentioning

confidence: 99%

Spatial Super Resolution of Real-World Aerial Images for Image-Based Plant Phenotyping

et al. 2021

View full text Add to dashboard Cite

Unmanned aerial vehicle (UAV) imaging is a promising data acquisition technique for image-based plant phenotyping. However, UAV images have a lower spatial resolution than similarly equipped in field ground-based vehicle systems, such as carts, because of their distance from the crop canopy, which can be particularly problematic for measuring small-sized plant features. In this study, the performance of three deep learning-based super resolution models, employed as a pre-processing tool to enhance the spatial resolution of low resolution images of three different kinds of crops were evaluated. To train a super resolution model, aerial images employing two separate sensors co-mounted on a UAV flown over lentil, wheat and canola breeding trials were collected. A software workflow to pre-process and align real-world low resolution and high-resolution images and use them as inputs and targets for training super resolution models was created. To demonstrate the effectiveness of real-world images, three different experiments employing synthetic images, manually downsampled high resolution images, or real-world low resolution images as input to the models were conducted. The performance of the super resolution models demonstrates that the models trained with synthetic images cannot generalize to real-world images and fail to reproduce comparable images with the targets. However, the same models trained with real-world datasets can reconstruct higher-fidelity outputs, which are better suited for measuring plant phenotypes.

show abstract

Section: Deep Learning-based Super Resolutionmentioning

confidence: 99%

Spatial Super Resolution of Real-World Aerial Images for Image-Based Plant Phenotyping

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In order to ensure that the degraded images have a similar noise distribution as the source images , we extract the noise mapping patches directly from the source images in the training dataset. Due to the large variance of the patches with rick contents [38], and inspired by [40,45], when extracting noise mapping patches we control the variance within a specific range under the condition:…”

Section: Generation and Injection Of Noisementioning

confidence: 99%

Super-Resolution of Sentinel-2 Images at 10m Resolution without Reference Images

Y¹,

B²

2021

Preprint

View full text Add to dashboard Cite

Sentinel-2 can provide multi-spectral optical remote sensing images in RGBN bands with a spatial resolution of 10m, but the spatial details provided are not enough for many applications. WorldView can provide HR multi-spectral images less than 2m, but it is a commercial paid resource with relatively high usage costs. In this paper, without any available reference images, Sentinel-2 images at 10m resolution are improved to a resolution of 2.5m through super-resolution (SR) based on deep learning technology. Our model, named DKN-SR-GAN, uses degradation kernel estimation and noise injection to construct a dataset of near-natural low-high-resolution (LHR) image pairs, with only low-resolution (LR) images and no high-resolution (HR) prior information. DKN-SR-GAN uses the Generative Adversarial Networks (GAN) combined of ESRGAN-type generator, PatchGAN-type discriminator and the VGG-19-type feature extractor, using perceptual loss to optimize the network, so as to obtain SR images with clearer details and better perceptual effects. Experiments demonstrate that in the quantitative comparison of the non-reference image quality assessment (NR-IQA) metrics like NIQE, BRISQUE and PIQE, as well as the intuitive visual effects of the generated images, compared with state-of-the-art models such as EDSR8-RGB, RCAN and RS-ESRGAN, our proposed model has obvious advantages.

show abstract

“…Recently, Zhang et al [33] proposed Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to optimize the generator in the direction of perceptual metrics, which achieved visually pleasing results and reached state-of-the-art performance in perceptual metrics. Zhou and Susstrunk [34] proposed KMSR to build the realistic blurkernel pool with GAN, and used it to construct real photograph paired dataset for unsupervised training. Lugmayr et al [35] also presented an unsupervised SR model through CycleGAN, which can transfer the LR image from bicubic degradation domain to real-world degradation domain, in this way, real world LR-HR paired training and testing datasets are formed.…”

Section: A Cnn-based Image Super-resolutionmentioning

confidence: 99%

Multi-Resolution Space-Attended Residual Dense Network for Single Image Super-Resolution

et al. 2020

View full text Add to dashboard Cite

With the help of deep convolutional neural networks, a vast majority of single image superresolution (SISR) methods have been developed, and achieved promising performance. However, these methods suffer from over-smoothness in textured regions due to utilizing a single-resolution network to reconstruct both the low-frequency and high-frequency information simultaneously. To overcome this problem, we propose a Multi-resolution space-Attended Residual Dense Network (MARDN) to separate lowfrequency and high-frequency information for reconstructing high-quality super-resolved images. Specifically, we start from a low-resolution sub-network, and add low-to-high resolution sub-networks step by step in several stages. These sub-networks with different depth and resolution are utilized to produce feature maps of different frequencies in parallel. For instance, the high-resolution sub-network with fewer stages is applied to local high-frequency textured information extraction, while the low-resolution one with more stages is devoted to generating global low-frequency information. Furthermore, the fusion block with channelwise sub-network attention is proposed for adaptively fusing the feature maps from different sub-networks instead of applying concatenation and 1 × 1 convolution. A series of ablation investigations and model analyses validate the effectiveness and efficiency of our MARDN. Extensive experiments on benchmark datasets demonstrate the superiority of the proposed MARDN against the state-of-the-art methods. Our super-resolution results and the source code can be downloaded from https://github.com/Periter/MARDN.

show abstract

Kernel Modeling Super-Resolution on Real Low-Resolution Images

Cited by 159 publications

References 47 publications

Spatial Super Resolution of Real-World Aerial Images for Image-Based Plant Phenotyping

Spatial Super Resolution of Real-World Aerial Images for Image-Based Plant Phenotyping

Super-Resolution of Sentinel-2 Images at 10m Resolution without Reference Images

Multi-Resolution Space-Attended Residual Dense Network for Single Image Super-Resolution

Contact Info

Product

Resources

About