检索结果-南通市图书馆

Neural 3D reconstruction from sparse views using geometric priors

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2023年第4期9卷 687-697页

作者： Tai-Jiang Mu Hao-Xiang Chen Jun-Xiong Cai Ning Guo BNRist Department of Computer Science and TechnologyTsinghua UniversityBeijing 100084China Academy of Military Sciences Beijing 100091China

Sparse view 3D reconstruction has attracted increasing attention with the development of neural implicit 3D representation.Existing methods usually only make use of 2D views,requiring a dense set of input views for accurate 3D reconstruction.In this paper,we show that accurate 3D reconstruction can be achieved by incorporating geometric priors into neural implicit 3D reconstruction.Our method adopts the signed distance function as the 3D representation,and learns a generalizable 3D surface reconstruction model from sparse views.Specifically,we build a more effective and sparse feature volume from the input views by using corresponding depth maps,which can be provided by depth sensors or directly predicted from the input views.We recover better geometric details by imposing both depth and surface normal constraints in addition to the color loss when training the neural implicit 3D representation.Experiments demonstrate that our method both outperforms state-of-the-art approaches,and achieves good generalizability.

关键词： sparse views 3D reconstruction volume rendering geometric priors neural implicit 3D representation

Millisecond dynamics of colloidal suspension studied by X-ray photon correlation spectroscopy at the Shanghai Synchrotron Radiation Facility

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2024年第1期35卷 1-9页

作者： Chen-Hui Cui Zi-mu Zhou Lin-Feng Wei Song-Lin Li Feng Tian Xiu-Hong Li Zhi Guo Yi-Hui Xu Huai-Dong jiang Ren-Zhong tai Shanghai Synchrotron Radiation Facility Shanghai Advanced Research InstituteChinese Academy of SciencesShanghai 201204China School of Physical Science and Technology ShanghaiTech UniversityShanghai 201210China Shanghai Institute of Applied Physics Chinese Academy of SciencesShanghai 201800China University of Chinese Academy of Sciences Chinese Academy of SciencesBeijing 100049China Center for Transformative Science ShanghaiTech UniversityShanghai 201210China

X-ray photon correlation spectroscopy(XPCS)has emerged as a powerful tool for probing the nanoscale dynamics of soft condensed matter and strongly correlated materials owing to its high spatial resolution and penetration capabilities.This technique requires high brilliance and beam coherence,which are not directly available at modern synchrotron beamlines in China.To facilitate future XPCS experiments,we modified the optical setup of the newly commissioned BL10U1 USAXS beamline at the Shanghai Synchrotron Radiation Facility(SSRF).Subsequently,we performed XPCS measurements on silica suspensions in glycerol,which were opaque owing to their high concentrations.Images were collected using a high frame rate area detector.A comprehensive analysis was performed,yielding correlation functions and several key dynamic parameters.All the results were consistent with the theory of Brownian motion and demonstrated the feasibility of XPCS at SSRF.Finally,by carefully optimizing the setup and analyzing the algorithms,we achieved a time resolution of 2 ms,which enabled the characterization of millisecond dynamics in opaque systems.

关键词： XPCS SSRF Silica suspension Glycerol Brownian motion Millisecond dynamics

Attention mechanisms in computer vision:A survey

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2022年第3期8卷 331-368页

作者： Meng-Hao Guo Tian-Xing Xu jiang-jiang Liu Zheng-Ning Liu Peng-Tao jiang Tai-Jiang Mu Song-Hai Zhang Ralph R.Martin Ming-Ming Cheng Shi-Min Hu BNRist Department of Computer Science and TechnologyTsinghua UniversityBeijing 100084China TKLNDST College of Computer ScienceNankai UniversityTianjin 300350China School of Computer Science and Informatics Cardiff UniversityCardiffUK

Humans can naturally and effectively find salient regions in complex scenes.Motivated by this observation,attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual system.Such an attention mechanism can be regarded as a dynamic weight adjustment process based on features of the input image.Attention mechanisms have achieved great success in many visual tasks,including image classification,object detection,semantic segmentation,video understanding,image generation,3D vision,multimodal tasks,and self-supervised learning.In this survey,we provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach,such as channel attention,spatial attention,temporal attention,and branch attention;a related repository https://***/MenghaoG uo/Awesome-Vision-Attentions is dedicated to collecting related work.We also suggest future directions for attention mechanism research.

关键词： attention transformer computer vision deep learning salience

ZNF554 Inhibits Endometrial Cancer Progression via Regulating RBM5 and Inactivating WNT/β-Catenin Signaling Pathway

在线全文

学校读者我要写书评

暂无评论

Current Medical Science 2024年第2期44卷 406-418页

作者： Cheng-cheng ZHU Heng-liang SUN Teng-fei LONG Yuan-yuan LYU jiang-li LIU Guan-tai NI Anhui Medical University Hefei 230032China Department of Obstetrics and Gynecology The First Afiliated Hospital of Wannan Medical CollegeWuhu 241001China

Objective:Uterine corpus endometrial carcinoma(UCEC),a kind of gynecologic malignancy,poses a significant risk to women’s health.The precise mechanism underlying the development of UCEC remains elusive.Zinc finger protein 554(ZNF554),a member of the Krüppel-associated box domain zinc finger protein superfamily,was reported to be dysregulated in various illnesses,including malignant tumors.This study aimed to examine the involvement of ZNF554 in the development of UCEC.Methods:The expression of ZNF554 in UCEC tissues and cell lines were examined by qRT-PCR and Western blot assay.Cells with stably overexpressed or knocked-down ZNF554 were established through lentivirus infection.CCK-8,wound healing,and Transwell invasion assays were employed to assess cell proliferation,migration,and invasion.Propidium iodide(PI)staining combined with fluorescence-activated cell sorting(FACS)flow cytometer was utilized to detect cell cycle distribution.qRT-PCR and Western blotting were conducted to examine relative mRNA and protein levels.Chromatin immunoprecipitation assay and luciferase reporter assay were used to explore the regulatory role of ZNF554 in RNA binding motif 5(RBM5).Results:The expression of ZNF554 was found to be reduced in both UCEC samples and cell lines.Decreased expression of ZNF554 was associated with higher tumor stage,decreased overall survival,and reduced disease-free survival in UCEC.ZNF554 overexpression suppressed cell proliferation,migration,and invasion,while also inducing cell cycle arrest.In contrast,a decrease in ZNF554 expression resulted in the opposite effect.Mechanistically,ZNF554 transcriptionally regulated RBM5,leading to the deactivation of the Wingless(WNT)/β-catenin signaling pathway.Moreover,the findings from rescue studies demonstrated that the inhibition of RBM5 negated the impact of ZNF554 overexpression onβ-catenin and p-glycogen synthase kinase-3β(p-GSK-3β).Similarly,the deliberate activation of RBM5 reduced the increase inβ-catenin and p-GSK-3βcaused by the suppression of ZNF554.In v

关键词： zinc finger protein 554 endometrial carcinoma RNA binding motif 5 Wingless/β-catenin signaling pathway

Detecting human-object interaction with multi-level pairwise feature network

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2021年第2期7卷 229-239页

作者： Hanchao Liu Tai-Jiang Mu Xiaolei Huan Key Laboratory of Pervasive Computing Ministry of EducationBNRistDepartment of Computer Science and TechnologyTsinghua UniversityBeijing 100084China College of Information Sciences and Technology Pennsylvania State UniversityUniversity ParkPA 16802USA.

Human–object interaction(HOI)detection is crucial for human-centric image understanding which aims to infer human,action,object triplets within an image.Recent studies often exploit visual features and the spatial configuration of a human–object pair in order to learn the action linking the human and object in the pair.We argue that such a paradigm of pairwise feature extraction and action inference can be applied not only at the whole human and object instance level,but also at the part level at which a body part interacts with an object,and at the semantic level by considering the semantic label of an object along with human appearance and human–object spatial configuration,to infer the action.We thus propose a multi-level pairwise feature network(PFNet)for detecting human–object interactions.The network consists of three parallel streams to characterize HOI utilizing pairwise features at the above three levels;the three streams are finally fused to give the action prediction.Extensive experiments show that our proposed PFNet outperforms other state-of-the-art methods on the VCOCO dataset and achieves comparable results to the state-of-the-art on the HICO-DET dataset.

关键词： human–object interaction detection pairwise feature network deep learning multi-level object instance

Synthesizing Robot Programs with Interactive Tutor Mode

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2019年第4期16卷 462-474页

作者： Hao Li Yu-Ping Wang Tai-Jiang Mu Tsinghua National Laboratory for Information Science and Technology(TNList) Department of Computer Science and TechnologyTsinghua University

With the rapid development of the robotic industry, domestic robots have become increasingly popular. As domestic robots are expected to be personal assistants, it is important to develop a natural language-based human-robot interactive system for end-users who do not necessarily have much programming knowledge. To build such a system, we developed an interactive tutoring framework, named " Holert”, which can translate task descriptions in natural language to machine-interpretable logical forms automatically. Compared to previous works, Holert allows users to teach the robot by further explaining their intentions in an interactive tutor mode. Furthermore, Holert introduces a semantic dependency model to enable the robot to " understand” similar task descriptions. We have deployed Holert on an open-source robot platform, Turtlebot 2. Experimental results show that the system accuracy could be significantly improved by 163.9% with the support of the tutor mode. This system is also efficient. Even the longest task session with 10 sentences can be handled within 0.7 s.

关键词： Human-robot interaction semantic parsing program synthesis intelligent robotic systems natural language unders-tanding

HDR-Net-Fusion:Real-time 3D dynamic scene reconstruction with a hierarchical deep reinforcement network

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2021年第4期7卷 419-435页

作者： Hao-Xuan Song Jiahui Huang Yan-Pei Cao Tai-Jiang Mu BNRist Department of Computer Science and TechnologyTsinghua UniversityBeiing 100084China Kuaishou Technology Co. Ltd.Beijing 100085China

Reconstructing dynamic scenes with commodity depth cameras has many applications in computer graphics,computer vision,and robotics.However,due to the presence of noise and erroneous observations from data capturing devices and the inherently ill-posed nature of non-rigid registration with insufficient information,traditional approaches often produce low-quality geometry with holes,bumps,and misalignments.We propose a novel 3D dynamic reconstruction system,named HDR-Net-Fusion,which learns to simultaneously reconstruct and refine the geometry on the fly with a sparse embedded deformation graph of surfels,using a hierarchical deep reinforcement(HDR)network.The latter comprises two parts:a global HDR-Net which rapidly detects local regions with large geometric errors,and a local HDR-Net serving as a local patch refinement operator to promptly complete and enhance such regions.Training the global HDR-Net is formulated as a novel reinforcement learning problem to implicitly learn the region selection strategy with the goal of improving the overall reconstruction quality.The applicability and efficiency of our approach are demonstrated using a large-scale dynamic reconstruction dataset.Our method can reconstruct geometry with higher quality than traditional methods.

关键词： dynamic 3D scene reconstruction deep reinforcement learning point cloud completion deep neural networks

A new dataset of dog breed images and a benchmark for fine-grained classification

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2020年第4期6卷 477-487页

作者： Ding-Nan Zou Song-Hai Zhang Tai-Jiang Mu Min Zhang Department of Computer Science and Technology BNRistTsinghua UniversityBeijing 100084China NaJiu Company Hunan 410022China Harvard Medical School Brigham and Women’s HospitalBostonMA 02115USA

In this paper, we introduce an image dataset for fine-grained classification of dog breeds: the Tsinghua Dogs Dataset. It is currently the largest dataset for fine-grained classification of dogs, including 130 dog breeds and 70,428 real-world images. It has only one dog in each image and provides annotated bounding boxes for the whole body and head. In comparison to previous similar datasets, it contains more breeds and more carefully chosen images for each breed. The diversity within each breed is greater,with between 200 and 7000+ images for each breed.Annotation of the whole body and head makes the dataset not only suitable for the improvement of finegrained image classification models based on overall features, but also for those locating local informative parts. We show that dataset provides a tough challenge by benchmarking several state-of-the-art deep neural models. The dataset is available for academic purposes at https://***/ThuDogs/.

关键词： fine-grained classification dog dataset benchmark

SpinNet: Spinning convolutional network for lane boundary detection

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2019年第4期5卷 417-428页

作者： Ruochen Fan Xuanrun Wang Qibin Hou Hanchao Liu Tai-Jiang Mu Tsinghua University Beijing100084China Nankai University Tianjin300350China

In this paper,we propose a simple but effective framework for lane boundary detection,called Spin Net.Considering that cars or pedestrians often occlude lane boundaries and that the local features of lane boundaries are not distinctive,therefore,analyzing and collecting global context information is crucial for lane boundary detection.To this end,we design a novel spinning convolution layer and a brand-new lane parameterization branch in our network to detect lane boundaries from a global perspective.To extract features in narrow strip-shaped fields,we adopt stripshaped convolutions with kernels which have 1×n or n×1 shape in the spinning convolution layer.To tackle the problem of that straight strip-shaped convolutions are only able to extract features in vertical or horizontal directions,we introduce the concept of feature map rotation to allow the convolutions to be applied in multiple directions so that more information can be collected concerning a whole lane boundary.Moreover,unlike most existing lane boundary detectors,which extract lane boundaries from segmentation masks,our lane boundary parameterization branch predicts a curve expression for the lane boundary for each pixel in the output feature map.And the network utilizes this information to predict the weights of the curve,to better form the final lane boundaries.Our framework is easy to implement and end-to-end trainable.Experiments show that our proposed Spin Net outperforms state-of-the-art methods.

关键词： object detection lane boundary detection autonomous driving deep learning