paper-with-me

홈 › Papers

Perceptual Extreme Super Resolution Network with Receptive Field Block

2020-05-26 · Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo

Perceptual Extreme Super-Resolution for single image is extremely difficult, because the texture details of different images vary greatly. To tackle this difficulty, we develop a super resolution network with receptive field block based on Enhanced SRGAN. We call our network RFB-ESRGAN. The key contributions are listed as follows. First, for the purpose of extracting multi-scale information and enhance the feature discriminability, we applied receptive field block (RFB) to super resolution. RFB has achieved competitive results in object detection and classification. Second, instead of using large convolution kernels in multi-scale receptive field block, several small kernels are used in RFB, which makes us be able to extract detailed features and reduce the computation complexity. Third, we alternately use different upsampling methods in the upsampling stage to reduce the high computation complexity and still remain satisfactory performance. Fourth, we use the ensemble of 10 models of different iteration to improve the robustness of model and reduce the noise introduced by each individual model. Our experimental results show the superior performance of RFB-ESRGAN. According to the preliminary results of NTIRE 2020 Perceptual Extreme Super-Resolution Challenge, our solution ranks first among all the participants.

📄 PDF Abstract BibTeX arXiv:2005.12597

Code (1)

Lornatang/RFB_ESRGAN-PyTorch pytorch

Tasks

Image Super-Resolutionobject-detectionObject DetectionSuper-Resolution

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
PReLU A Parametric Rectified Linear Unit, or PReLU, is an activation function that generalizes the traditional rectified unit with a slope for negative values.…
Sigmoid Activation 설명 없음
Ethereum Customer Service Number +1-833-534-1729 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Efficient Image Super-Resolution via Symmetric Visual Attention Network

2024-01-17 · Chengxu Wu, Qinrui Fan, Shu Hu, Xi Wu 외

An important development direction in the Single-Image Super-Resolution (SISR) algorithms is to improve the efficiency of the algorithms. Recently, efficient Super-Resolution (SR) research focuses on reducing model compl…

Image Super-ResolutionSuper-Resolution

Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification

2022-07-21 · Yongqiang Mao, Kaiqiang Chen, Wenhui Diao, Xian Sun 외

The classification of airborne laser scanning (ALS) point clouds is a critical task of remote sensing and photogrammetry fields. Although recent deep learning-based methods have achieved satisfactory performance, they ha…

ClassificationPoint Cloud Classification

NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results

2020-05-03 · Kai Zhang, Shuhang Gu, Radu Timofte, Taizhang Shang 외

This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor 16 based…

Image Super-ResolutionSuper-Resolution

Resolution-robust Large Mask Inpainting with Fourier Convolutions

2021-09-15 · Roman Suvorov, Elizaveta Logacheva, Anton Mashikhin, Anastasia Remizova 외

Modern image inpainting systems, despite the significant progress, often struggle with large missing areas, complex geometric structures, and high-resolution images. We find that one of the main reasons for that is the l…

Image InpaintingSeeing Beyond the Visible

FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution

2025-03-13 · Wenjie Li, Heng Guo, Yuefeng Hou, Zhanyu Ma

Image super-resolution (SR) aims to recover low-resolution images to high-resolution images, where improving SR efficiency is a high-profile challenge. However, commonly used units in SR, like convolutions and window-bas…

Image Super-ResolutionSuper-Resolution