paper-with-me

홈 › Papers

Adaptive Densely Connected Super-Resolution Reconstruction

2019-12-17 · Tangxin Xie, Xin Yang, Yu Jia, Chen Zhu, Xiaochuan Li

For a better performance in single image super-resolution(SISR), we present an image super-resolution algorithm based on adaptive dense connection (ADCSR). The algorithm is divided into two parts: BODY and SKIP. BODY improves the utilization of convolution features through adaptive dense connections. Also, we develop an adaptive sub-pixel reconstruction layer (AFSL) to reconstruct the features of the BODY output. We pre-trained SKIP to make BODY focus on high-frequency feature learning. The comparison of PSNR, SSIM, and visual effects verify the superiority of our method to the state-of-the-art algorithms.

📄 PDF Abstract BibTeX arXiv:1912.08002

Code (1)

xxh96/ADCSR pytorch

Tasks

Image Super-ResolutionSSIMSuper-Resolution

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Brain MRI Super Resolution Using 3D Deep Densely Connected Neural Networks

2018-01-08 · Yuhua Chen, Yibin Xie, Zhengwei Zhou, Feng Shi 외

Magnetic resonance image (MRI) in high spatial resolution provides detailed anatomical information and is often necessary for accurate quantitative analysis. However, high spatial resolution typically comes at the expens…

Deep LearningImage Super-ResolutionSuper-Resolution

Dual Reconstruction with Densely Connected Residual Network for Single Image Super-Resolution

2019-11-20 · Chih-Chung Hsu, Chia-Hsiang Lin

Deep learning-based single image super-resolution enables very fast and high-visual-quality reconstruction. Recently, an enhanced super-resolution based on generative adversarial network (ESRGAN) has achieved excellent p…

Generative Adversarial NetworkImage Super-ResolutionSSIMSuper-Resolution

Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Network

2018-03-04 · Yuhua Chen, Feng Shi, Anthony G. Christodoulou, Zhengwei Zhou 외

High-resolution (HR) magnetic resonance images (MRI) provide detailed anatomical information important for clinical application and quantitative image analysis. However, HR MRI conventionally comes at the cost of longer …

Generative Adversarial NetworkImage Super-ResolutionSuper-Resolution

DVNet: A Memory-Efficient Three-Dimensional CNN for Large-Scale Neurovascular Reconstruction

2020-02-04 · Leila Saadatifard, Aryan Mobiny, Pavel Govyadinov, Hien Nguyen 외

Maps of brain microarchitecture are important for understanding neurological function and behavior, including alterations caused by chronic conditions such as neurodegenerative disease. Techniques such as knife-edge scan…

DecoderSegmentationSemantic Segmentation

Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution

2021-06-13 · Huapeng Wu, Jie Gui, Jun Zhang, James T. Kwok 외

Recently, deep convolutional neural network methods have achieved an excellent performance in image superresolution (SR), but they can not be easily applied to embedded devices due to large memory cost. To solve this pro…

Image Super-ResolutionSuper-Resolution