Related papers: Can Ground Truth Label Propagation from Video help…

Fingerprint recognition on mobile devices is an important method for identity verification. However, real fingerprints usually contain sweat and moisture which leads to poor recognition performance. In addition, for rolling out slimmer and…

Graph Convolutional Networks (GCNs) suffer from severe performance degradation in deep architectures due to over-smoothing. While existing studies primarily attribute the over-smoothing to repeated applications of graph Laplacian operators,…

We propose 4 insights that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image. These insights are: (1) denoise the "ground truth" surface normals in…

Accurate three-dimensional perception is a fundamental task in several computer vision applications. Recently, commercial RGB-depth (RGB-D) cameras have been widely adopted as single-view depth-sensing devices owing to their efficient…

Convolutional video models have an order of magnitude larger computational complexity than their counterpart image-level models. Constrained by computational resources, there is no model or training method that can train long video…

Robot perception systems need to perform reliable image segmentation in real-time on noisy, raw perception data. State-of-the-art segmentation approaches use large CNN models and carefully constructed datasets; however, these models focus…

This study deals with semantic segmentation of high-resolution (aerial) images where a semantic class label is assigned to each pixel via supervised classification as a basis for automatic map generation. Recently, deep convolutional neural…

Numerous image processing techniques (IPTs) have been employed to detect crack defects, offering an alternative to human-conducted onsite inspections. These IPTs manipulate images to extract defect features, particularly cracks in surfaces…

Depth estimation provides essential information to perform autonomous driving and driver assistance. Especially, Monocular Depth Estimation is interesting from a practical point of view, since using a single camera is cheaper than many…

With the rapid development of Remote Sensing acquisition techniques, there is a need to scale and improve processing tools to cope with the observed increase of both data volume and richness. Among popular techniques in remote sensing, Deep…

Modern neural networks are usually highly over-parameterized. Behind the wide usage of over-parameterized networks is the belief that, if the data are simple, then the trained network will be automatically equivalent to a simple predictor.…

Annotating images for semantic segmentation requires intense manual labor and is a time-consuming and expensive task especially for domains with a scarcity of experts, such as Forensic Anthropology. We leverage the evolving nature of images…

Nowadays, vision-based computing tasks play an important role in various real-world applications. However, many vision computing tasks, e.g. semantic segmentation, are usually computationally expensive, posing a challenge to the computing…

Whole-body PET/CT scan is an important tool for diagnosing various malignancies (e.g., malignant melanoma, lymphoma, or lung cancer), and accurate segmentation of tumors is a key part for subsequent treatment. In recent years, CNN-based…

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

In convolutional neural networks (CNNs), padding plays a pivotal role in preserving spatial dimensions throughout the layers. Traditional padding techniques do not explicitly distinguish between the actual image content and the padded…

Semantic image segmentation is a principal problem in computer vision, where the aim is to correctly classify each individual pixel of an image into a semantic label. Its widespread use in many areas, including medical imaging and…

Recent work has shown that convolutional neural networks (CNNs) can be applied successfully in disparity estimation, but these methods still suffer from errors in regions of low-texture, occlusions and reflections. Concurrently, deep…

Multi-scale deep CNNs have been used successfully for problems mapping each pixel to a label, such as depth estimation and semantic segmentation. It has also been shown that such architectures are reusable and can be used for multiple…

In this work, we present a novel background subtraction system that uses a deep Convolutional Neural Network (CNN) to perform the segmentation. With this approach, feature engineering and parameter tuning become unnecessary since the…