Guided Deep Decoder: Unsupervised Image Pair Fusion
RIKEN AIP（理化学研究所革新智能综合研究中心）；German Aerospace Center（德国航空航天中心）；Univ. Grenoble Alpes（格勒诺布尔-阿尔卑斯大学）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工学院）；GIPSA-lab（格勒诺布尔图像语音信号自动控制实验室）；The University of Tokyo（东京大学）
Tatsumi Uezato, Danfeng Hong, Naoto Yokoya, Wei He
The fusion of input and guidance images that have a tradeoff in their information (e.g., hyperspectral and RGB image fusion or pansharpening) can be interpreted as one general problem. However, previous studies applied a task-specific handcrafted prior and did not address the problems with a unified approach. 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. The two networks are connected by feature refinement units to embed the multi-scale features of the guidance image into the deep decoder network. The proposed network allows the network parameters to be optimized in an unsupervised way without training data. Our results show that the proposed network can achieve state-of-the-art performance in various image fusion problems.
Unsupervised Hyperspectral and Multispectral Image Blind Fusion Based on Deep Tucker Decomposition Network with Spatial-Spectral Manifold Learning
School of Computer Science and Engineering, Nanjing University of Science and Technology (NJUST)（南京理工大学计算机科学与工程学院）；Geological Exploration Technology Institute of Jiangsu Province（江苏省地质勘查技术院）；Jiangsu Province Engineering Research Center of Airborne Detecting and Intelligent Perceptive Technology（江苏省机载探测与智能感知技术工程研究中心）
Sichuan University（四川大学）；University of British Columbia（不列颠哥伦比亚大学）；Xidian University（西安电子科技大学）；Incheon National University（仁川大学）；Shandong University of Technology（山东理工大学）
In computer vision and image processing tasks, image fusion has evolved into an attractive research field. However, recent existing image fusion methods are mostly built on pixel-level operations, which may produce unacceptable artifacts and are time-consuming. In this paper, a symmetric encoder-decoder with a residual block (SEDR) for infrared and visible image fusion is proposed. For the training stage, the SEDR network is trained with a new dataset to obtain a fixed feature extractor. For the fusion stage, first, the trained model is utilized to extract the intermediate features and compens…
Infrared and visible image fusion, a hot topic in the field of image processing, aims at obtaining fused images keeping the advantages of source images. This paper proposes a novel auto-encoder (AE) based fusion network. The core idea is that the encoder decomposes an image into background and detail feature maps with low- and high-frequency information, respectively, and that the decoder recovers the original image. To this end, the loss function makes the background/detail feature maps of source images similar/dissimilar. In the test phase, background and detail feature maps are respectively…
University of Science and Technology Beijing（北京科技大学）；Beijing Advanced Innovation Center for Materials Genome Engineering（北京材料基因工程高精尖创新中心）；School of Computer and Communication Engineering（计算机与通信工程学院）；Beijing Key Laboratory of Knowledge Engineering for Materials Science（北京市材料科学知识工程重点实验室）；Institute for Advanced Materials and Technology（先进材料与技术研究所）
In this work, we propose a novel unsupervised deep learning model to address multi-focus image fusion problem. First, we train an encoder-decoder network in unsupervised manner to acquire deep feature of input images. And then we utilize these features and spatial frequency to measure activity level and decision map. Finally, we apply some consistency verification methods to adjust the decision map and draw out fused result. The key point behind of proposed method is that only the objects within the depth-of-field (DOF) have sharp appearance in the photograph while other objects are likely to …
Jiangnan University（江南大学）；University of Surrey（萨里大学）
Deep learning-based image fusion approaches have obtained wide attention in recent years, achieving promising performance in terms of visual perception. However, the fusion module in the current deep learning-based methods suffers from two limitations, \textit{i.e.}, manually designed fusion function, and input-independent network learning. In this paper, we propose an unsupervised adaptive image fusion method to address the above issues. We propose a feature mutual mapping fusion module and dual-branch multi-scale autoencoder. More specifically, we construct a global map to measure the connec…
MAUGIF: Mechanism-Aware Unsupervised General Image Fusion via Dual Cross-Image Autoencoders
School of Mathematics, Hunan University（湖南大学数学学院）；College of Information Engineering, Zhejiang University of Technology（浙江工业大学信息工程学院）；Department of Electrical and Electronic Engineering, The University of Hong Kong（香港大学电子与电气工程系）
Visual Information Laboratory, University of Bristol（布里斯托大学视觉信息实验室）
A significant number of researchers have applied deep learning methods to image fusion. However, most works require a large amount of training data or depend on pre-trained models or frameworks to capture features from source images. This is inevitably hampered by a shortage of training data or a mismatch between the framework and the actual problem. Deep Image Prior (DIP) has been introduced to exploit convolutional neural networks' ability to synthesize the 'prior' in the input image. However, the original design of DIP is hard to be generalized to multi-image processing problems, particular…
Xidian University（西安电子科技大学）；The University of Western Australia（西澳大学）
Convolutional neural networks have recently been used for multi-focus image fusion. However, due to the lack of labeled data for supervised training of such networks, existing methods have resorted to adding Gaussian blur in focused images to simulate defocus and generate synthetic training data with ground-truth for supervised learning. Moreover, they classify pixels as focused or defocused and leverage the results to construct the fusion weight maps which then necessitates a series of post-processing steps. In this paper, we present unsupervised end-to-end learning for directly predicting th…
In this paper, we train independent linear decoder models to estimate the perceived quality of images. More specifically, we calculate the responses of individual non-overlapping image patches to each of the decoders and scale these responses based on the sharpness characteristics of filter set. We use multiple linear decoders to capture different abstraction levels of the image patches. Training each model is carried out on 100,000 image patches from the ImageNet database in an unsupervised fashion. Color space selection and ZCA Whitening are performed over these patches to enhance the descri…
The University of Tennessee（田纳西大学）；Applied Research LLC（应用研究有限责任公司）
In many computer vision applications, obtaining images of high resolution in both the spatial and spectral domains are equally important. However, due to hardware limitations, one can only expect to acquire images of high resolution in either the spatial or spectral domains. This paper focuses on hyperspectral image super-resolution (HSI-SR), where a hyperspectral image (HSI) with low spatial resolution (LR) but high spectral resolution is fused with a multispectral image (MSI) with high spatial resolution (HR) but low spectral resolution to obtain HR HSI. Existing deep learning-based solution…
Shanghai Jiao Tong University（上海交通大学）；University of Electronic Science and Technology of China（电子科技大学）；University of Calgary（卡尔加里大学）
The fusion of images taken by heterogeneous sensors helps to enrich the information and improve the quality of imaging. In this article, we present a hybrid model consisting of a convolutional encoder and a Transformer-based decoder to fuse multimodal images. In the encoder, a non-local cross-modal attention block is proposed to capture both local and global dependencies of multiple source images. A branch fusion module is designed to adaptively fuse the features of the two branches. We embed a Transformer module with linear complexity in the decoder to enhance the reconstruction capability of…
Liaoning Normal University（辽宁师范大学）；Dalian University of Technology（大连理工大学）
General deep learning-based methods for infrared and visible image fusion rely on the unsupervised mechanism for vital information retention by utilizing elaborately designed loss functions. However, the unsupervised mechanism depends on a well designed loss function, which cannot guarantee that all vital information of source images is sufficiently extracted. In this work, we propose a novel interactive feature embedding in self-supervised learning framework for infrared and visible image fusion, attempting to overcome the issue of vital information degradation. With the help of self-supervis…
Jiangnan University（江南大学）；University of Strathclyde（斯特拉斯克莱德大学）
In this paper we propose a novel method for infrared and visible image fusion where we develop nest connection-based network and spatial/channel attention models. The nest connection-based network can preserve significant amounts of information from input data in a multi-scale perspective. The approach comprises three key elements: encoder, fusion strategy and decoder respectively. In our proposed fusion strategy, spatial attention models and channel attention models are developed that describe the importance of each spatial position and of each channel with deep features. Firstly, the source …
In recent years, various applications in computer vision have achieved substantial progress based on deep learning, which has been widely used for image fusion and shown to achieve adequate performance. However, suffering from limited ability in modeling the spatial correspondence of different source images, it still remains a great challenge for existing unsupervised image fusion models to extract appropriate feature and achieves adaptive and balanced fusion. In this paper, we propose a novel cross-attention-guided image fusion network, which is a unified and unsupervised framework for multi-…
This paper presents a generative model method for multispectral image fusion in remote sensing which is trained without supervision. This method eases the supervision of learning and it also considers a multi-objective loss function to achieve image fusion. The loss function incorporates both spectral and spatial distortions. Two discriminators are designed to minimize the spectral and spatial distortions of the generative output. Extensive experimentations are conducted using three public domain datasets. The comparison results across four reduced-resolution and three full-resolution objectiv…
Staining reveals the micro structure of the aspirate while creating histopathology slides. Stain variation, defined as a chromatic difference between the source and the target, is caused by varying characteristics during staining, resulting in a distribution shift and poor performance on the target. The goal of stain normalization is to match the target's chromatic distribution to that of the source. However, stain normalisation causes the underlying morphology to distort, resulting in an incorrect diagnosis. We propose FUSION, a new method for promoting stain-adaption by adjusting the model t…
In this paper we present a new approach for feature fusion between RGB and LWIR Thermal images for the task of semantic segmentation for driving perception. We propose DooDLeNet, a double DeepLab architecture with specialized encoder-decoders for thermal and color modalities and a shared decoder for final segmentation. We combine two strategies for feature fusion: confidence weighting and correlation weighting. We report state-of-the-art mean IoU results on the MF dataset.
In this paper, we estimate perceived image quality using sparse representations obtained from generic image databases through an unsupervised learning approach. A color space transformation, a mean subtraction, and a whitening operation are used to enhance descriptiveness of images by reducing spatial redundancy; a linear decoder is used to obtain sparse representations; and a thresholding stage is used to formulate suppression mechanisms in a visual system. A linear decoder is trained with 7 GB worth of data, which corresponds to 100,000 8x8 image patches randomly obtained from nearly 1,000 i…
School of Computer Science and Engineering, Xi'an University of Technology（西安理工大学计算机科学与工程学院）
Image haze removal is highly desired for the application of computer vision. This paper proposes a novel Context Guided Generative Adversarial Network (CGGAN) for single image dehazing. Of which, an novel new encoder-decoder is employed as the generator. And it consists of a feature-extraction-net, a context-extractionnet, and a fusion-net in sequence. The feature extraction-net acts as a encoder, and is used for extracting haze features. The context-extraction net is a multi-scale parallel pyramid decoder, and is used for extracting the deep features of the encoder and generating coarse dehaz…
University of Toulouse（图卢兹大学）；IRIT/INP-ENSEEIHT（图卢兹大学综合理工学院图像与信号处理研究所（IRIT/INP-ENSEEIHT））
Unsupervised change detection techniques are generally constrained to two multi-band optical images acquired at different times through sensors sharing the same spatial and spectral resolution. This scenario is suitable for a straight comparison of homologous pixels such as pixel-wise differencing. However, in some specific cases such as emergency situations, the only available images may be those acquired through different kinds of sensors with different resolutions. Recently some change detection techniques dealing with images with different spatial and spectral resolutions, have been propos…
