Filters








20,395 Hits in 4.6 sec

Guided Deep Decoder: Unsupervised Image Pair Fusion [article]

Tatsumi Uezato, Danfeng Hong, Naoto Yokoya, Wei He
2020 arXiv   pre-print
To address this limitation, in this study, we propose a guided deep decoder network as a general prior.  ...  The proposed network is composed of an encoder-decoder network that exploits multi-scale features of a guidance image and a deep decoder network that generates an output image.  ...  In the following section, we propose a new architecture, called the guided deep decoder, as a regularizer that can be used for various image fusion problems.  ... 
arXiv:2007.11766v1 fatcat:kb4sox3mqjd7xd352joj53fzca

Cross-Modal Image Fusion Theory Guided by Subjective Visual Attention [article]

Aiqing Fang, Xinbo Zhao, Yanning Zhang
2019 arXiv   pre-print
The image fusion theory effectively unifies the subjective task intention and prior knowledge of human brain.  ...  In order to improve the robustness and contextual awareness of image fusion tasks, we proposed a multi-task auxiliary learning image fusion theory guided by subjective attention.  ...  the deep learning weight model for image fusion.  ... 
arXiv:1912.10718v1 fatcat:4fgrayc4wjdolcey4vspg3miuy

Fast and Efficient Zero-Learning Image Fusion [article]

Fayez Lahoud, Sabine Süsstrunk
2019 arXiv   pre-print
We propose a real-time image fusion method using pre-trained neural networks. Our method generates a single image containing features from multiple sources.  ...  We use visual saliency to fuse the base layers, and deep feature maps extracted from a pre-trained neural network to fuse the detail layers.  ...  ACKNOWLEDGMENT We thankfully acknowledge the support of the Hasler Foundation (grant no. 16076, S.A.V.E.) for this work.  ... 
arXiv:1905.03590v1 fatcat:o75pg6dfgjckbd2hy57ciuhd5a

A Dark and Bright Channel Prior Guided Deep Network for Retinal Image Quality Assessment [article]

Ziwen Xu, Beiji Zou, Qing Liu
2021 arXiv   pre-print
This paper proposes a dark and bright channel prior guided deep network for retinal image quality assessment called GuidedNet.  ...  Current state-of-the-arts either directly transfer classification networks originally designed for natural images to quality classification of retinal images or introduce extra image quality priors via  ...  (c) Our proposed prior guided single branch network. Fig. 2 . 2 Examples for dark and bright channel priors of different quality retinal images.  ... 
arXiv:2010.13313v2 fatcat:gyyvy772ofdwva3cqgxavw3q6e

Knowing Depth Quality In Advance: A Depth Quality Assessment Method For RGB-D Salient Object Detection [article]

Xuehao Wang, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin
2020 arXiv   pre-print
To be more concrete, we conduct D quality assessments for each image region, following a multi-scale methodology that includes low-level edge consistency, mid-level regional uncertainty and high-level  ...  However, such fully automatic fusions may not always be helpful for the SOD task because the D quality itself usually varies from scene to scene.  ...  Moreover, for those images with high-quality D, our method can still outperform other SOTA methods.  ... 
arXiv:2008.04157v1 fatcat:ypoajgewwzd7fci3hljjpylgzu

Deep Learning-based Face Super-Resolution: A Survey [article]

Junjun Jiang, Chenyang Wang, Xianming Liu, Jiayi Ma
2021 arXiv   pre-print
Face super-resolution (FSR), also known as face hallucination, which is aimed at enhancing the resolution of low-resolution (LR) face images to generate high-resolution (HR) face images, is a domain-specific  ...  image super-resolution problem.  ...  Single-face guided methods set the problem as an LR face image only has one high-quality reference face image, but in some applications many high-quality face images are available, and they can further  ... 
arXiv:2101.03749v2 fatcat:q56d2mpn4rfyzmi5fo36d2ecja

A Cross-Modal Image Fusion Method Guided by Human Visual Characteristics [article]

Aiqing Fang and Xinbo Zhao and Jiaqi Yang and Yanning Zhang
2020 arXiv   pre-print
Then, we analyze the impact of the existing image fusion loss on the image fusion quality, and establish the multi-loss function model of unsupervised learning network.  ...  multi-focus image public data set for experimental verification.  ...  The main task network is mainly used for cross-modal image fusion task, and the two subnetworks are image reconstruction task network and multi-focus image fusion network.  ... 
arXiv:1912.08577v4 fatcat:lajicugsc5cllpjzihqag6tcda

An Overview of Underwater Vision Enhancement: From Traditional Methods to Recent Deep Learning

Kai Hu, Chenghang Weng, Yanwen Zhang, Junlan Jin, Qingfeng Xia
2022 Journal of Marine Science and Engineering  
Firstly, this paper analyzes the imaging principle of underwater images and the reasons for their decline in quality and briefly classifies various existing methods.  ...  Degenerated images have adverse effects on the visual tasks of underwater vehicles, such as recognition and detection. Therefore, it is vital to obtain high-quality underwater video images.  ...  [74] used a group of image quality measures to guide the restoration process based on the CNN network.  ... 
doi:10.3390/jmse10020241 fatcat:mxifcm2lkjgkfdj3y4u4wtrgxm

UMAG-Net: A New Unsupervised Multiattention-Guided Network for Hyperspectral and Multispectral Image Fusion

Shuaiqi Liu, Siyu Miao, Jian Su, Bing Li, Weiming Hu, Yu-Dong Zhang
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Index Terms-Deep learning, hyperspectral images (HSIs), image fusion, multispectral images (MSIs).  ...  In order to break the limits, we construct an unsupervised multiattention-guided network named UMAG-Net without training data to better accomplish HSI-MSI fusion.  ...  [35] proposed a guided deep decoder (GDD) network, which can be applied for image denoising and image fusion without training.  ... 
doi:10.1109/jstars.2021.3097178 fatcat:kxoiq4fyc5c4bjhhjceig4xdpq

Deep Fusion Prior for Multi-Focus Image Super Resolution Fusion [article]

Yuanjie Gu, Zhibo Xiao, Hailun Wang, Cheng Liu, Shouyu Wang
2022 arXiv   pre-print
unsupervised framework named deep fusion prior (DFP) to address such MFISRF task.  ...  In particular, DFP can obtain MFISRF only from two low-resolution inputs without any extent dataset; SKIPnet implementing unsupervised learning via deep image prior is an end-to-end generated network acting  ...  In particular, SKIPnet implementing unsupervised learning via deep image prior is an end-to-end generated network acting as the engine of DFP.  ... 
arXiv:2110.05706v2 fatcat:jvjqphlxpra75jolxt4reoq5ey

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 6885-6897 Deep Graph-Convolutional Image Denoising. Valsesia, D., +, TIP 2020 8226-8237 Deep Guided Learning for Fast Multi-Exposure Image Fusion.  ...  ., +, TIP 2020 1016-1029 Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition. Liu, Y., +, TIP 2020 3168-3182 Deep Ranking for Image Zero-Shot Multi-Label Classification.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Spatial-Spectral Fusion by Combining Deep Learning and Variation Model [article]

Huanfeng Shen, Menghui Jiang, Jie Li, Qiangqiang Yuan, Yanchong Wei,, Liangpei Zhang
2018 arXiv   pre-print
Then we construct a fusion framework by the LR-MS image, the gradient prior learned from the gradient network, and the ideal fused image.  ...  This paper presents a fusion method that incorporates the deep neural network into the model-based method for the most common case in the spatial-spectral fusion: PAN/multispectral (MS) fusion.  ...  makes a high-quality fusion performance.  ... 
arXiv:1809.00764v1 fatcat:nezi7fcbvnclxhcpic6bpqc3ya

Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation [article]

Cheng Ma, Zhenyu Jiang, Yongming Rao, Jiwen Lu, Jie Zhou
2020 arXiv   pre-print
Recent works based on deep learning and facial priors have succeeded in super-resolving severely degraded facial images.  ...  Quantitative and qualitative experimental results show the proposed method significantly outperforms state-of-the-art FSR methods in recovering high-quality face images.  ...  We design a deep iterative collaboration network which estimates high-quality SR images and landmark maps iteratively and progressively with the input LR images.  ... 
arXiv:2003.13063v1 fatcat:ivo5477i4fffzbyk44j2yqjrwi

Table of contents

2020 IEEE Transactions on Image Processing  
Kim 710 RYF-Net: Deep Fusion Network for Single Image Haze Removal .......................... A. Dudhane and S.  ...  X. 2653 Semi-Supervised Image Dehazing .................. L.Li, Y. Dong, W. Ren, J. Pan, C. Gao, N. Sang, and M.-H. Yang 2766 Deep Guided Learning for Fast Multi-Exposure Image Fusion ...  ... 
doi:10.1109/tip.2019.2940373 fatcat:i7hktzn4wrfz5dhq7hj75u6esa

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TIP 2021 6226-6239 Deep Coupled Feedback Network for Joint Exposure Fusion and Image Super-Resolution.  ...  ., +, TIP 2021 5905-5919 Triply Complementary Priors for Image Restoration. Zha, Z., +, TIP 2021 5819-5834 Ultra High Fidelity Deep Image Decompression With l ∞ -Constrained Com-pression.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu
« Previous Showing results 1 — 15 out of 20,395 results