Related papers: Depth Estimation using Weighted-loss and Transfer …

Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint…

Transformer and its variants have shown state-of-the-art results in many vision tasks recently, ranging from image classification to dense prediction. Despite of their success, limited work has been reported on improving the model…

Knowledge about historic landslide event occurrence is important for supporting disaster risk reduction strategies. Building upon findings from 2022 Landslide4Sense Competition, we propose a deep neural network based system for landslide…

Deep image registration has demonstrated exceptional accuracy and fast inference. Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner. However, due…

This paper presents an edge-based defocus blur estimation method from a single defocused image. We first distinguish edges that lie at depth discontinuities (called depth edges, for which the blur estimate is ambiguous) from edges that lie…

Deep learning approaches have shown promising performance for compressed sensing-based Magnetic Resonance Imaging. While deep neural networks trained with mean squared error (MSE) loss functions can achieve high peak signal to noise ratio,…

Convolutional Neural Networks (ConvNets) have successfully contributed to improve the accuracy of regression-based methods for computer vision tasks such as human pose estimation, landmark localization, and object detection. The network…

Gravity exploration has become an important geophysical method due to its low cost and high efficiency. With the rise of artificial intelligence, data-driven gravity inversion methods based on deep learning (DL) possess physical property…

Transfer learning for feature extraction can be used to exploit deep representations in contexts where there is very few training data, where there are limited computational resources, or when tuning the hyper-parameters needed for training…

Currently, most deep learning methods cannot solve the problem of scarcity of industrial product defect samples and significant differences in characteristics. This paper proposes an unsupervised defect detection algorithm based on a…

In this study, we explore the application of deep learning techniques for predicting cleansing quality in colon capsule endoscopy (CCE) images. Using a dataset of 500 images labeled by 14 clinicians on the Leighton-Rex scale (Poor, Fair,…

Efficiently deploying deep neural networks on low-resource edge devices is challenging due to their ever-increasing resource requirements. To address this issue, researchers have proposed multiplication-free neural networks, such as…

Event cameras offer a promising avenue for multi-view stereo depth estimation and Simultaneous Localization And Mapping (SLAM) due to their ability to detect blur-free 3D edges at high-speed and over broad illumination conditions. However,…

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

Omnidirectional depth sensing has its advantage over the conventional stereo systems since it enables us to recognize the objects of interest in all directions without any blind regions. In this paper, we propose a novel wide-baseline…

Image and video restoration has achieved a remarkable leap with the advent of deep learning. The success of deep learning paradigm lies in three key components: data, model, and loss. Currently, many efforts have been devoted to the first…

In many computer vision tasks, for example saliency prediction or semantic segmentation, the desired output is a foreground map that predicts pixels where some criteria is satisfied. Despite the inherently spatial nature of this task…

The top-k error is a common measure of performance in machine learning and computer vision. In practice, top-k classification is typically performed with deep neural networks trained with the cross-entropy loss. Theoretical results indeed…

Semantic segmentation is a core task in computer vision with applications in biomedical imaging, remote sensing, and autonomous driving. While standard loss functions such as cross-entropy and Dice loss perform well in general cases, they…

Seismic data often contain gaps due to various obstacles in the investigated area and recording instrument failures. Deep learning techniques offer promising solutions for reconstructing missing data parts by leveraging existing…