Related papers: HITNet: Hierarchical Iterative Tile Refinement Net…
Stereo vision generally involves the computation of pixel correspondences and estimation of disparities between rectified image pairs. In many applications, including simultaneous localization and mapping (SLAM) and 3D object detection, the…
Low-dose CT (LDCT) imaging is desirable in many clinical applications to reduce X-ray radiation dose to patients. Inspired by deep learning (DL), a recent promising direction of model-based iterative reconstruction (MBIR) methods for LDCT…
Depth estimation is one of the key technologies in some fields such as autonomous driving and robot navigation. However, the traditional method of using a single sensor is inevitably limited by the performance of the sensor. Therefore, a…
Predicting depth from a single image is an attractive research topic since it provides one more dimension of information to enable machines to better perceive the world. Recently, deep learning has emerged as an effective approach to…
Recent studies shows that the majority of existing deep steganalysis models have a large amount of redundancy, which leads to a huge waste of storage and computing resources. The existing model compression method cannot flexibly compress…
Spiking Neural Networks are often touted as brain-inspired learning models for the third wave of Artificial Intelligence. Although recent SNNs trained with supervised backpropagation show classification accuracy comparable to deep networks,…
Leveraging the disparity information from both left and right views is crucial for stereo disparity estimation. Left-right consistency check is an effective way to enhance the disparity estimation by referring to the information from the…
Semantic segmentation is a popular research topic in computer vision, and many efforts have been made on it with impressive results. In this paper, we intend to search an optimal network structure that can run in real-time for this problem.…
We propose AuralNet, a novel 3D multi-source binaural sound source localization approach that localizes overlapping sources in both azimuth and elevation without prior knowledge of the number of sources. AuralNet employs a gated…
Stereo matching, a critical step of 3D reconstruction, has fully shifted towards deep learning due to its strong feature representation of remote sensing images. However, ground truth for stereo matching task relies on expensive airborne…
New technologies drastically change recruitment techniques. Some research projects aim at designing interactive systems that help candidates practice job interviews. Other studies aim at the automatic detection of social signals (e.g.…
Current works on multi-person 3D pose estimation mainly focus on the estimation of the 3D joint locations relative to the root joint and ignore the absolute locations of each pose. In this paper, we propose the Human Depth Estimation…
Stereo matching is a significant part in many computer vision tasks and driving-based applications. Recently cost volume-based methods have achieved great success benefiting from the rich geometry information in paired images. However, the…
3D convolutional neural networks have revealed superior performance in processing volumetric data such as video and medical imaging. However, the competitive performance by leveraging 3D networks results in huge computational costs, which…
Many applications of stereo depth estimation in robotics require the generation of accurate disparity maps in real time under significant computational constraints. Current state-of-the-art algorithms force a choice between either…
Heterogeneous information networks(HINs) become popular in recent years for its strong capability of modelling objects with abundant information using explicit network structure. Network embedding has been proved as an effective method to…
Understanding and leveraging the 3D structures of proteins is central to a variety of biological and drug discovery tasks. While deep learning has been applied successfully for structure-based protein function prediction tasks, current…
This paper introduces HPNet, a novel deep-learning approach for segmenting a 3D shape represented as a point cloud into primitive patches. The key to deep primitive segmentation is learning a feature representation that can separate points…
We present a real-time, non-learning depth estimation method that fuses Light Detection and Ranging (LiDAR) data with stereo camera input. Our approach comprises three key techniques: Semi-Global Matching (SGM) stereo with Discrete…
Real-time performance of stereo matching networks is important for many applications, such as automatic driving, robot navigation and augmented reality (AR). Although significant progress has been made in stereo matching networks in recent…