scispace - formally typeset
Search or ask a question
Topic

Upsampling

About: Upsampling is a research topic. Over the lifetime, 2426 publications have been published within this topic receiving 57613 citations.


Papers
More filters
Posted Content
TL;DR: Li et al. as mentioned in this paper proposed a fully convolutional multi-stage neural network for face image super-resolution, which is composed of a stem layer, a residual backbone, and spatial upsampling layers.
Abstract: To make the best use of the underlying structure of faces, the collective information through face datasets and the intermediate estimates during the upsampling process, here we introduce a fully convolutional multi-stage neural network for 4$\times$ super-resolution for face images. We implicitly impose facial component-wise attention maps using a segmentation network to allow our network to focus on face-inherent patterns. Each stage of our network is composed of a stem layer, a residual backbone, and spatial upsampling layers. We recurrently apply stages to reconstruct an intermediate image, and then reuse its space-to-depth converted versions to bootstrap and enhance image quality progressively. Our experiments show that our face super-resolution method achieves quantitatively superior and perceptually pleasing results in comparison to state of the art.

10 citations

Proceedings ArticleDOI
01 Dec 2019
TL;DR: In this article, the authors generalize untrained and underparametrized non-convolutional architectures to signals defined over irregular domains represented by graphs and incorporate upsampling operators accounting for the structure of the supporting graph, which is achieved by considering a systematic graph coarsening approach based on hierarchical clustering.
Abstract: While deep convolutional architectures have achieved remarkable results in a gamut of supervised applications dealing with images and speech, recent works show that deep untrained non-convolutional architectures can also outperform state-of-the-art methods in several tasks such as image compression and denoising. Motivated by the fact that many contemporary datasets have an irregular structure different from a 1D/2D grid, this paper generalizes untrained and underparametrized non-convolutional architectures to signals defined over irregular domains represented by graphs. The proposed architecture consists of a succession of layers, each of them implementing an upsampling operator, a linear feature combination, and a scalar nonlinearity. A novel element is the incorporation of upsampling operators accounting for the structure of the supporting graph, which is achieved by considering a systematic graph coarsening approach based on hierarchical clustering. The numerical results carried out in synthetic and real-world datasets showcase that the reconstruction performance can improve drastically if the information of the supporting graph topology is taken into account.

10 citations

Patent
03 Mar 1999
TL;DR: In this paper, a delay circuit is applied to derive samples of the input signal representing spatially separated elements from each field of chrominance information, where the spatial separation is of one line and the sizes of the samples are compared relative to one another to identify frequencies which fall within different high and low frequency ranges.
Abstract: The present invention relates to filtering an interlaced input digital signal containing fields of chrominance information preparatory to converting the format of the signal by means of a downsampling conversion from a 4:2:2 format to a 4:2:0 format. In the invention, the input signal is applied to a delay circuit to derive samples of the input signal representing spatially separated elements from each chrominance field where the spatial separation is of one line. The magnitudes of the samples are compared relative to one another to identify frequencies which fall within different high and low frequency ranges. An adaptive filter has a plurality of frequency responses corresponding to the frequency ranges and a frequency response is selected in accordance with the identified frequency range of the input signal samples.

10 citations

Journal ArticleDOI
TL;DR: An improved PSPNet network architecture named shift pooling PSPNet is proposed, which uses a module called shift pyramid Pooling to replace the original pyramid pooling module, so that the pixels at the edge of the grid can also obtain the entire local features.
Abstract: Building extraction by deep learning from remote sensing images is currently a research hotspot. PSPNet is one of the classic semantic segmentation models and is currently adopted by many applications. Moreover, PSPNet can use not only CNN-based networks but also transformer-based networks as backbones; therefore, PSPNet also has high value in the transformer era. The core of PSPNet is the pyramid pooling module, which gives PSPNet the ability to capture the local features of different scales. However, the pyramid pooling module also has obvious shortcomings. The grid is fixed, and the pixels close to the edge of the grid cannot obtain the entire local features. To address this issue, an improved PSPNet network architecture named shift pooling PSPNet is proposed, which uses a module called shift pyramid pooling to replace the original pyramid pooling module, so that the pixels at the edge of the grid can also obtain the entire local features. Shift pooling is not only useful for PSPNet but also in any network that uses a fixed grid for downsampling to increase the receptive field and save computing, such as ResNet. A dense connection was adopted in decoding, and upsampling was gradually carried out. With two open datasets, the improved PSPNet, PSPNet, and some classic image segmentation models were used for comparative experiments. The results show that our method is the best according to the evaluation metrics, and the predicted image is closer to the label.

10 citations

Book ChapterDOI
01 Jan 2022
TL;DR: Zhang et al. as discussed by the authors proposed a retinal vessel segmentation network with dual branch transformer module and adaptive strip upsampling (DA-Net), which can simultaneously and fully enjoy the patches-level local information and the image-level global context.
Abstract: Since the morphology of retinal vessels plays a pivotal role in clinical diagnosis of eye-related diseases and diabetic retinopathy, retinal vessels segmentation is an indispensable step for the screening and diagnosis of retinal diseases, yet it is still a challenging problem due to the complex structure of retinal vessels. Current retinal vessels segmentation approaches roughly fall into image-level and patches-level methods based on the input type, while each has its own strengths and weaknesses. To benefit from both of the input forms, we introduce a Dual Branch Transformer Module (DBTM) that can simultaneously and fully enjoy the patches-level local information and the image-level global context. Besides, the retinal vessels are long-span, thin, and distributed in strips, making the square kernel of classic convolutional neural network false as it is only suitable for most natural objects with bulk shape. To better capture context information, we further design an Adaptive Strip Upsampling Block (ASUB) to adapt to the striped distribution of the retinal vessels. Based on the above innovations, we propose a retinal vessels segmentation Network with Dual Branch Transformer and Adaptive Strip Upsampling (DA-Net). Experiments validate that our DA-Net outperforms other state-of-the-art methods on both DRIVE and CHASE-DB1 datasets.

10 citations


Network Information
Related Topics (5)
Convolutional neural network
74.7K papers, 2M citations
90% related
Image segmentation
79.6K papers, 1.8M citations
90% related
Feature extraction
111.8K papers, 2.1M citations
89% related
Deep learning
79.8K papers, 2.1M citations
88% related
Feature (computer vision)
128.2K papers, 1.7M citations
87% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023469
2022859
2021330
2020322
2019298
2018236