检索结果-内蒙古大学图书馆

Graph-based parallel large scale structure from motion

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chen, Yu Shen, Shuhan Chen, Yisong Wang, Guoping Graphics and Interactive Lab Department of Computer Science and Technology School of Electronic Engineering and Computer Science Peking University National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

While Structure from Motion (SfM) achieves great success in 3D reconstruction, it still meets challenges on large scale scenes. In this work, large scale SfM is deemed as a graph problem, and we tackle it in a divide-and-conquer manner. Firstly, the images clustering algorithm divides images into clusters with strong connectivity, leading to robust local reconstructions. Then followed with an image expansion step, the connection and completeness of scenes are enhanced by expanding along with a maximum spanning tree. After local reconstructions, we construct a minimum spanning tree (MST) to find accurate similarity transformations. Then the MST is transformed into a Minimum Height Tree (MHT) to find a proper anchor node and is further utilized to prevent error accumulation. When evaluated on different kinds of datasets, our approach shows superiority over the state-of-the-art in accuracy and efficiency. Our algorithm is open-sourced in https://***/AIBluefisher/GraphSfM. Copyright © 2019, The Authors. All rights reserved.

关键词： Clustering algorithms

Discovery of Novel Androgen Receptor Ligands by Structure-based Virtual Screening and Bioassays

学校读者我要写书评

暂无评论

Genomics, Proteomics & Bioinformatics 2018年第6期16卷 416-427页

作者： Wenfang Zhou Mojie Duan Weitao Fu Jinping Pang Qin Tang Huiyong Sun Lei Xu Shan Chang Dan Li Tingjun Hou College of Pharmaceutical Sciences Zhejiang University State Key Laboratory of Computer Aided Design and Computer Graphics (CAD&GC) Zhejiang University State Key Laboratory of Magnetic Resonance and Atomic and Molecular Physics National Center for Magnetic Resonance in WuhanWuhan Institute of Physics and MathematicsChinese Academy of Sciences Institute of Bioinformatics and Medical Engineering School of Electrical and Information EngineeringJiangsu University of Technology

Androgen receptor(AR) is a ligand-activated transcription factor that plays a pivotal role in the development and progression of many severe diseases such as prostate cancer, muscle atrophy, and osteoporosis. Binding of ligands to AR triggers the conformational changes in AR that may affect the recruitment of coactivators and downstream response of AR signaling ***, AR ligands have great potential to treat these diseases. In this study, we searched for novel AR ligands by performing a docking-based virtual screening(VS) on the basis of the crystal structure of the AR ligand binding domain(LBD) in complex with its agonist. A total of 58 structurally diverse compounds were selected and subjected to LBD affinity assay, with five of them(HBP1-3, HBP1-17, HBP1-38, HBP1-51, and HBP1-58) exhibiting strong binding to AR-LBD. The IC50 values of HBP1-51 and HBP1-58 are 3.96 m M and 4.92 m M, respectively, which are even lower than that of enzalutamide(Enz, IC50= 13.87 m M), a marketed second-generation AR antagonist. Further bioactivity assays suggest that HBP1-51 is an AR agonist, whereas HBP1-58 is an AR antagonist. In addition, molecular dynamics(MD) simulations and principal components analysis(PCA) were carried out to reveal the binding principle of the newlyidentified AR ligands toward AR. Our modeling results indicate that the conformational changes of helix 12 induced by the bindings of antagonist and agonist are visibly different. In summary,the current study provides a highly efficient way to discover novel AR ligands, which could serve as the starting point for development of new therapeutics for AR-related diseases.

关键词： Androgen receptor AR ligand Virtual screening AR agonist AR antagonist

Apple Vision Pro for Healthcare: "The Ultimate Display"? Entering the Wonderland of Precision Medicine

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Egger, Jan Gsaxner, Christina Chen, Xiaojun Bian, Jiang Kleesiek, Jens Puladi, Behrus Girardetstraße 2 Essen45131 Germany Hufelandstraße 55 Essen45147 Germany Hufelandstraße 55 Essen45147 Germany Department of Oral and Maxillofacial Surgery University Hospital RWTH Aachen Pauwelsstraße 30 Aachen52074 Germany Institute of Computer Graphics and Vision Graz University of Technology Inffeldgasse 16/II Graz8010 Austria Institute of Biomedical Manufacturing and Life Quality Engineering State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Dongchuan Road 800 Minhang District Shanghai200240 China Institute of Medical Robotics Shanghai Jiao Tong University Dongchuan Road 800 Minhang District Shanghai200240 China Health Outcomes & Biomedical Informatics College of Medicine University of Florida GainesvilleFL32610 United States Partner Site Essen Hufelandstraße 55 Essen45147 Germany Department of Physics TU Dortmund University August-Schmidt-Str. 4 Dortmund44227 Germany Institute of Medical Informatics University Hospital RWTH Aachen Pauwelsstraße 30 Aachen52074 Germany

At the Worldwide Developers Conference (WWDC) in June 2023, Apple introduced the Vision Pro. The Vision Pro is a Mixed Reality (MR) headset, more specifically it is a Virtual Reality (VR) device with an additional Video See-Through (VST) capability. The VST capability turns the Vision Pro also into an Augmented Reality (AR) device. The AR feature is enabled by streaming the real world via cameras to the (VR) screens in front of the user’s eyes. This is of course not unique and similar to other devices, like the Varjo XR-3. Nevertheless, the Vision Pro has some interesting features, like an inside-out screen that can show the headset wearers’ eyes to "outsiders" or a button on the top, called "Digital Crown", that allows you to seamlessly blend digital content with your physical space by turning it. In addition, it is untethered, except for the cable to the battery, which makes the headset more agile, compared to the Varjo XR-3. This could actually come closer to the "Ultimate Display", which Ivan Sutherland had already sketched in 1965. Not available to the public yet, like the Ultimate Display, we want to take a look into the crystal ball in this perspective to see if it can overcome some clinical challenges that - especially - AR still faces in the medical domain, but also go beyond and discuss if the Vision Pro could support clinicians in essential tasks to spend more time with their patients. © 2023, CC BY.

关键词： Augmented reality

Automating visual data processing to support post-earthquake reconnaissance 11

学校读者我要写书评

暂无评论

Automating visual data processing to support post-earthquake...

11th National Conference on Earthquake Engineering 2018: Integrating Science, Engineering, and Policy, NCEE 2018

作者： Yeum, C.M. Dyke, S.J. Benes, B. Hacker, T. Ramirez, J. Lund, A. Sim, C. Pujol, S. Lyles School of Civil Eng. Purdue University IN47906 United States Computer Graphics Technology Purdue University IN47906 United States Computer and Information Technology Purdue University IN47906 United States School of Civil Eng. University of Nebraska IN47906 United States

ISBN: (纸本)9781510873254

Each extreme seismic event is an opportunity to assess the performance of our infrastructure under circumstances that cannot entirely be reproduced in the laboratory or through numerical simulation. When performing reconnaissance in the field, engineers record much of the information being gathered in the form of images. When large quantities of images are collected within a short time period and have such a wide variety of content, timely organization and documentation will be important. Clearly, manual sorting and analysis of all these images would be prohibitively tedious and expensive. Thus, to efficiently and thoroughly use these images, engineers need to exploit recent advances in computer vision and machine learning. Herein we introduce a series of automated capabilities we have developed, based on computer vision and machine learning, to classify, organize, and document the large volumes of visual data collected during a reconnaissance mission. We illustrate two specific techniques that can significantly enhance current data collection and organization procedures to support reconnaissance missions: automated (1) reconnaissance report generation, and (2) structural drawing reconstruction. © NCEE *** rights reserved.

关键词： computer vision

Deep 2.5D vehicle classification with sparse SfM depth prior for automated toll systems

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Waltner, Georg Maurer, Michael Holzmann, Thomas Ruprecht, Patrick Opitz, Michael Possegger, Horst Fraundorfer, Friedrich Bischof, Horst Institute of Computer Graphics and Vision Faculty of Computer Science Graz University of Technology Graz8010 Austria

Automated toll systems rely on proper classification of the passing vehicles. This is especially difficult when the images used for classification only cover parts of the vehicle. To obtain information about the whole vehicle. we reconstruct the vehicle as 3D object and exploit this additional information within a Convolutional Neural Network (CNN). However, when using deep networks for 3D object classification, large amounts of dense 3D models are required for good accuracy, which are often neither available nor feasible to process due to memory requirements. Therefore, in our method we reproject the 3D object onto the image plane using the reconstructed points, lines or both. We utilize this sparse depth prior within an auxiliary network branch that acts as a regularizer during training. We show that this auxiliary regularizer helps to improve accuracy compared to 2D classification on a real-world dataset. Furthermore due to the design of the network, at test time only the 2D camera images are required for classification which enables the usage in portable computer vision systems. Copyright © 2018, The Authors. All rights reserved.

关键词： Classification (of information)

When world(view)s collide: Contested epistemologies and ontologies in transdisciplinary education∗

学校读者我要写书评

暂无评论

When world(view)s collide: Contested epistemologies and onto...

作者： Gray, Colin M Fernandez, Todd M Department of Computer Graphics Technology Purdue University West LafayetteIN47907 United States School of Engineering Education Purdue University West LafayetteIN47907 United States

In conjunction with the drive towards human-centered design in engineering education, questions arise regarding how students build and engage a socially-Aware engineering identity, and how this identity points towards beliefs about the nature of reality. In this paper, we describe how students in a transdisciplinary undergraduate program struggle to engage with ontological and epistemological perspectives that draw on this social turn, particularly in relation to human-centered engineering approaches and sociotechnical complexity. We use a critical qualitative meaning reconstruction approach to deeply analyze the meaning-making assumptions of the students. Our findings reveal characteristic barriers in engaging with other subjectivities, and related epistemological and ontological claims implicit in these subjectivities. Specifically, we show that students' observable behaviors often mask misalignments between their epistemic beliefs and the designerly practices they employ-failing to account for the multiple subjective realities that the tools are designed to uncover. For these students, that misalignment makes the learning or practice of designerly behaviors less formative of a designerly identity. We conclude with implications for encouraging socially-Aware identity formation in engineering education. # 2018 TEMPUS Publications. © 2018 Tempus Publications. All rights reserved.

关键词： Students

Deep metric learning with BIER: Boosting independent embeddings robustly

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Opitz, Michael Waltner, Georg Possegger, Horst Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria

Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of embeddings. In this work, we show how to improve the robustness of such embeddings by exploiting the independence within ensembles. To this end, we divide the last embedding layer of a deep network into an embedding ensemble and formulate training this ensemble as an online gradient boosting problem. Each learner receives a reweighted training sample from the previous learners. Further, we propose two loss functions which increase the diversity in our ensemble. These loss functions can be applied either for weight initialization or during training. Together, our contributions leverage large embedding sizes more effectively by significantly reducing correlation of the embedding and consequently increase retrieval accuracy of the embedding. Our method works with any differentiable loss function and does not introduce any additional parameters during test time. We evaluate our metric learning method on image retrieval tasks and show that it improves over state-of-the-art methods on the CUB-200-2011, Cars-196, Stanford Online Products, In-Shop Clothes Retrieval and VehicleID datasets. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

PRS-Net: Planar reflective symmetry detection net for 3D models

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Gao, Lin Zhang, Ling-Xiao Meng, Hsien-Yu Ren, Yi-Hui Lai, Yu-Kun Kobbelt, Leif Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Maryland College ParkMD United States Visual Computing Group School of Computer Science and Informatics Cardiff University Wales United Kingdom Institute for Computer Graphics and Multimedia RWTH Aachen University Aachen Germany

In geometry processing, symmetry is a universal type of high-level structural information of 3D models and benefits many geometry processing tasks including shape segmentation, alignment, matching, and completion. Thus it is an important problem to analyze various symmetry forms of 3D shapes. Planar reflective symmetry is the most fundamental one. Traditional methods based on spatial sampling can be time-consuming and may not be able to identify all the symmetry planes. In this paper, we present a novel learning framework to automatically discover global planar reflective symmetry of a 3D shape. Our framework trains an unsupervised 3D convolutional neural network to extract global model features and then outputs possible global symmetry parameters, where input shapes are represented using voxels. We introduce a dedicated symmetry distance loss along with a regularization loss to avoid generating duplicated symmetry planes. Our network can also identify generalized cylinders by predicting their rotation axes. We further provide a method to remove invalid and duplicated planes and axes. We demonstrate that our method is able to produce reliable and accurate results. Our neural network based method is hundreds of times faster than the state-of-the-art methods, which are based on sampling. Our method is also robust even with noisy or incomplete input surfaces. Copyright © 2019, The Authors. All rights reserved.

关键词： Geometry

Generalized feedback loop for joint hand-object pose estimation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Oberweger, Markus Wohlhart, Paul Lepetit, Vincent Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Laboratoire Bordelais de Recherche en Informatique Université de Bordeaux Bordeaux France X Alphabet Inc. Mountain ViewCA United States

We propose an approach to estimating the 3D pose of a hand, possibly handling an object, given a depth image. We show that we can correct the mistakes made by a Convolutional Neural Network trained to predict an estimate of the 3D pose by using a feedback loop. The components of this feedback loop are also Deep Networks, optimized using training data. This approach can be generalized to a hand interacting with an object. Therefore, we jointly estimate the 3D pose of the hand and the 3D pose of the object. Our approach performs en-par with state-of-the-art methods for 3D hand pose estimation, and outperforms state-of-the-art methods for joint hand-object pose estimation when using depth images only. Also, our approach is efficient as our implementation runs in real-time on a single GPU. Copyright © 2019, The Authors. All rights reserved.

关键词： Feedback