Výsledky vyhľadávania - "IEEE transactions on image processing"

Vision Transformers for Single Image Dehazing Autor Song, Yuda, He, Zhuqing, Qian, Hui, Du, Xin

“…Image dehazing is a representative low-level vision task that estimates latent haze-free images from hazy images. In recent years, convolutional neural…”
Získať plný text

UIU-Net: U-Net in U-Net for Infrared Small Object Detection Autor Wu, Xin, Hong, Danfeng, Chanussot, Jocelyn

“…Learning-based infrared small object detection methods currently rely heavily on the classification backbone network. This tends to result in tiny object loss…”
Získať plný text

EnlightenGAN: Deep Light Enhancement Without Paired Supervision Autor Jiang, Yifan, Gong, Xinyu, Liu, Ding, Cheng, Yu, Fang, Chen, Shen, Xiaohui, Yang, Jianchao, Zhou, Pan, Wang, Zhangyang

“…Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of…”
Získať plný text

Dense Nested Attention Network for Infrared Small Target Detection Autor Li, Boyang, Xiao, Chao, Wang, Longguang, Wang, Yingqian, Lin, Zaiping, Li, Miao, An, Wei, Guo, Yulan

“…Single-frame infrared small target (SIRST) detection aims at separating small targets from clutter backgrounds. With the advances of deep learning, CNN-based…”
Získať plný text

DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention Autor Chen, Zixuan, He, Zewei, Lu, Zhe-Ming

Získať plný text

DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention Autor Chen, Zixuan, He, Zewei, Lu, Zhe-Ming

“…Single image dehazing is a challenging ill-posed problem which estimates latent haze-free images from observed hazy images. Some existing deep learning based…”
Získať plný text

nnFormer: Volumetric Medical Image Segmentation via a 3D Transformer Autor Zhou, Hong-Yu, Guo, Jiansen, Zhang, Yinghao, Han, Xiaoguang, Yu, Lequan, Wang, Liansheng, Yu, Yizhou

“…Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community. Given the ability to exploit…”
Získať plný text

U-shape Transformer for Underwater Image Enhancement Autor Peng, Lintao, Zhu, Chunli, Bian, Liheng

“…The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The existing data-driven based underwater image…”
Získať plný text

Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding Autor Li, Chongyi, Anwar, Saeed, Hou, Junhui, Cong, Runmin, Guo, Chunle, Ren, Wenqi

“…Underwater images suffer from color casts and low contrast due to wavelength-and distance-dependent attenuation and scattering. To solve these two degradation…”
Získať plný text

LayerCAM: Exploring Hierarchical Class Activation Maps for Localization Autor Jiang, Peng-Tao, Zhang, Chang-Bin, Hou, Qibin, Cheng, Ming-Ming, Wei, Yunchao

“…The class activation maps are generated from the final convolutional layer of CNN. They can highlight discriminative object regions for the class of interest…”
Získať plný text

Underwater Image Enhancement via Minimal Color Loss and Locally Adaptive Contrast Enhancement Autor Zhang, Weidong, Zhuang, Peixian, Sun, Hai-Han, Li, Guohou, Kwong, Sam, Li, Chongyi

“…Underwater images typically suffer from color deviations and low visibility due to the wavelength-dependent light absorption and scattering. To deal with these…”
Získať plný text

An Underwater Image Enhancement Benchmark Dataset and Beyond Autor Li, Chongyi, Guo, Chunle, Ren, Wenqi, Cong, Runmin, Hou, Junhui, Kwong, Sam, Tao, Dacheng

“…Underwater image enhancement has been attracting much attention due to its significance in marine engineering and aquatic robotics. Numerous underwater image…”
Získať plný text

Weighted Feature Fusion of Convolutional Neural Network and Graph Attention Network for Hyperspectral Image Classification Autor Dong, Yanni, Liu, Quanwei, Du, Bo, Zhang, Liangpei

“…Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN), such as Graph Attention Networks (GAT), are two classic neural network models, which are…”
Získať plný text

CGNet: A Light-weight Context Guided Network for Semantic Segmentation Autor Wu, Tianyi, Tang, Sheng, Rui, Zhang, Cao, Juan, Zhang, Yongdong

“…The demand of applying semantic segmentation model on mobile devices has been increasing rapidly. Current state-of-the-art networks have enormous amount of…”
Získať plný text

DenseFuse: A Fusion Approach to Infrared and Visible Images Autor Li, Hui, Wu, Xiao-Jun

“…In this paper, we present a novel deep learning architecture for infrared and visible images fusion problems. In contrast to conventional convolutional…”
Získať plný text

Fast Parameter-Free Multi-View Subspace Clustering With Consensus Anchor Guidance Autor Wang, Siwei, Liu, Xinwang, Zhu, Xinzhong, Zhang, Pei, Zhang, Yi, Gao, Feng, Zhu, En

“…Multi-view subspace clustering has attracted intensive attention to effectively fuse multi-view information by exploring appropriate graph structures. Although…”
Získať plný text

FoveaBox: Beyound Anchor-Based Object Detection Autor Kong, Tao, Sun, Fuchun, Liu, Huaping, Jiang, Yuning, Li, Lei, Shi, Jianbo

“…We present FoveaBox, an accurate, flexible, and completely anchor-free framework for object detection. While almost all state-of-the-art object detectors…”
Získať plný text

Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement Autor Yang, Wenhan, Wang, Wenjing, Huang, Haofeng, Wanga, Shiqi, Liu, Jiaying

“…Due to the absence of a desirable objective for low-light image enhancement, previous data-driven methods may provide undesirable enhanced results including…”
Získať plný text

Benchmarking Single-Image Dehazing and Beyond Autor Li, Boyi, Ren, Wenqi, Fu, Dengpan, Tao, Dacheng, Feng, Dan, Zeng, Wenjun, Wang, Zhangyang

“…We present a comprehensive study and evaluation of existing single-image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic…”
Získať plný text

DDcGAN: A Dual-discriminator Conditional Generative Adversarial Network for Multi-resolution Image Fusion Autor Ma, Jiayi, Xu, Han, Jiang, Junjun, Mei, Xiaoguang, Zhang, Xiao-Ping

“…In this paper, we proposed a new end-to-end model, termed as dual-discriminator conditional generative adversarial network (DDcGAN), for fusing infrared and…”
Získať plný text