Search

This paper tackles spectral reflectance recovery (SRR) from RGB images. Since capturing ground-truth spectral reflectance and camera spectral sensitivity are challenging and costly, most existing approaches are trained on synthetic images and utilize the same parameters for all unseen testing images, which are suboptimal especially when the trained models are tested on real images because they never exploit the internal information of the testing images. To address this issue, we adopt a self-supervised meta-auxiliary learning (MAXL) strategy that fine-tunes the well-trained network parameters with each testing image to combine external with internal information. To the best of our knowledge, this is the first work that successfully adapts the MAXL strategy to this problem. Instead of relying on naive end-to-end training, we also propose a novel architecture that integrates the physical relationship between the spectral reflectance and the corresponding RGB images into the network based on our mathematical analysis. Besides, since the spectral reflectance of a scene is independent to its illumination while the corresponding RGB images are not, we recover the spectral reflectance of a scene from its RGB images captured under multiple illuminations to further reduce the unknown. Qualitative and quantitative evaluations demonstrate the effectiveness of our proposed network and of the MAXL. Our code and data are available at https://github.com/Dong-Huo/SRR-MAXL.

Amyotrophic Lateral Sclerosis (ALS) is a complex neurodegenerative disorder involving motor neuron degeneration. Significant research has begun to establish brain magnetic resonance imaging (MRI) as a potential biomarker to diagnose and monitor the state of the disease. Deep learning has turned into a prominent class of machine learning programs in computer vision and has been successfully employed to solve diverse medical image analysis tasks. However, deep learning-based methods applied to neuroimaging have not achieved superior performance in ALS patients classification from healthy controls due to having insignificant structural changes correlated with pathological features. Therefore, the critical challenge in deep models is to determine useful discriminative features with limited training data. By exploiting the long-range relationship of image features, this study introduces a framework named SF2Former that leverages vision transformer architecture's power to distinguish the ALS subjects from the control group. To further improve the network's performance, spatial and frequency domain information are combined because MRI scans are captured in the frequency domain before being converted to the spatial domain. The proposed framework is trained with a set of consecutive coronal 2D slices, which uses the pre-trained weights on ImageNet by leveraging transfer learning. Finally, a majority voting scheme has been employed to those coronal slices of a particular subject to produce the final classification decision. Our proposed architecture has been thoroughly assessed with multi-modal neuroimaging data using two well-organized versions of the Canadian ALS Neuroimaging Consortium (CALSNIC) multi-center datasets. The experimental results demonstrate the superiority of our proposed strategy in terms of classification accuracy compared with several popular deep learning-based techniques., Comment: 17 pages, 8 figures

Many deep learning based methods are designed to remove non-uniform (spatially variant) motion blur caused by object motion and camera shake without knowing the blur kernel. Some methods directly output the latent sharp image in one stage, while others utilize a multi-stage strategy (\eg multi-scale, multi-patch, or multi-temporal) to gradually restore the sharp image. However, these methods have the following two main issues: 1) The computational cost of multi-stage is high; 2) The same convolution kernel is applied in different regions, which is not an ideal choice for non-uniform blur. Hence, non-uniform motion deblurring is still a challenging and open problem. In this paper, we propose a new architecture which consists of multiple Atrous Spatial Pyramid Deformable Convolution (ASPDC) modules to deblur an image end-to-end with more flexibility. Multiple ASPDC modules implicitly learn the pixel-specific motion with different dilation rates in the same layer to handle movements of different magnitude. To improve the training, we also propose a reblurring network to map the deblurred output back to the blurred input, which constrains the solution space. Our experimental results show that the proposed method outperforms state-of-the-art methods on the benchmark datasets. The code is available at https://github.com/Dong-Huo/ASPDC., CVPRW 2022

Texture analysis is a well-known research topic in computer vision and image processing and has many applications. Gradient-based texture methods have become popular in classification problems. For the first time we extend a well-known gradient-based method, Co-occurrence Histograms of Oriented Gradients (CoHOG) to extract texture features from 2D Magnetic Resonance Images (MRI). Unlike the original CoHOG method, we use the whole image instead of sub-regions for feature calculation. Also, we use a larger neighborhood size. Gradient orientations of the image pixels are calculated using Sobel, Gaussian Derivative (GD) and Local Frequency Descriptor Gradient (LFDG) operators. The extracted feature vector size is very large and classification using a large number of similar features does not provide the best results. In our proposed method, for the first time to our best knowledge, only a minimum number of significant features are selected using area under the receiver operator characteristic (ROC) curve (AUC) thresholds with, We found an error in the feature selection part (Sec. 3.3) of the proposed approach. In the feature selection part, by mistake, we have used both the training and testing data for feature selection. We are working on it. We will update the proposed approach as early as possible

In this paper, we present the design and development of an undersea camera system. The goal of our system is to provide a 3D model of the undersea habitat in a long-term continuous manner. The most important feature of our system is the use of multiple cameras and multiple projectors, which is able to provide accurate 3D models with an accuracy of a millimeter. By introducing projectors in our system, we can use many different structured light methods for different tasks. There are two main advantages comparing our system with using ROVs or AUVs. First, our system can provide continuous monitoring of the undersea habitat. Second, our system has a low hardware cost. Comparing to existing deployed camera systems, the advantage of our system is that it can provide accurate 3D models and provides opportunities for future development of innovative algorithms for undersea research.

This paper presents a novel, simple, yet powerful texture analysis method inspired by the well-known Local Binary Patterns (LBP) method called the Local Frequency Descriptors (LFD). Like LBP, the proposed method is invariant to rotation and linear changes of illumination; however,it does not suffer from the limitations of LBP such as exponential growth of features with an increment in the number of neighbors. The experimental results on the Outex and CUReT datasets show that the proposed LFD method outperforms state-of-the-art texture analysis methods. In addition, LFD is very robust to noise and can improve LBP results up to 50% in extremely noisy conditions. In this paper, we discuss different aspects of the LFD and explain how it addresses the main limitations of LBP and of its variants. | TRID-ID TR12-03