检索结果-内蒙古大学图书馆

1st International Conference on Extended reality, ICXR 2024

作者： Li, Lu Zhu, Xia Ni, Shaofeng Gao, Fan Cao, Dinglun Pei, Ziyi Li, Shuai State Grid Location based Service Co. Ltd Beijing China State Grid Information & Telecommunication Group Co. Ltd. Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (纸本)9789819636785

Remote sensing images are essential for various applications such as environmental monitoring and urban planning. However, the spatial resolution of these images often hinders the accurate detection of small-scale or densely packed targets. In this work, we advocate a novel method that introduces clustering into local super-resolution networks to enhance image resolution and improve the detectability of small-scale and dense regions. First, K-means clustering is applied to identify dense areas based on both the color and spatial properties of image pixels, efficiently pinpointing regions where small objects are concentrated. Next, a lightweight cross-attention-based super-resolution network is employed to enhance the resolution of these key regions, which improves object detection accuracy. The proposed method is computationally efficient, incorporating depthwise separable convolutions and focusing the cross-attention mechanism on regions of interest, thereby minimizing overhead. Extensive experiments on the WV-3 and DOTA datasets demonstrate that our method significantly improves image quality, outperforming existing methods in terms of both PSNR and SSIM. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Text-driven 3D Human Generation via Contrastive Preference Optimization

arXiv

引用

arXiv 2025年

作者： Zhou, Pengfei Shen, Xukun Hu, Yong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China

Recent advancements in Score Distillation Sampling (SDS) have significantly improved text-driven 3D human generation, enabling plausible synthesis from natural language descriptions. However, existing methods struggle with fine-grained semantic alignment, leading to inconsistencies in structure, texture, and attribute representation. To address these challenges, we propose a contrastive preference modeling framework that integrates both positive and negative prompts to enhance SDS. This approach refines text-conditioned generation, improving semantic consistency and 3D fidelity. Specifically, we introduce a preference optimization module that aggregates knowledge from multiple preference models to ensure accurate representation of intricate attributes and nuanced details. Additionally, we propose a negation preference module with static-dynamic negation prompts to systematically distinguish relevant details from extraneous elements, ensuring geometric and textural consistency. To further mitigate artifacts and prevent reward hacking, we develop an LLM-driven dynamic negation prompting mechanism that analyzes textual inputs, decomposes complex attributes, and filters irrelevant components. Extensive experiments demonstrate that our method achieves state-of-the-art performance, significantly enhancing texture realism, structure coherence, and overall visual alignment, particularly for complex and lengthy textual descriptions. © 2025, CC BY.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Dense object detection for remote sensing images based on multi-scale partitioning and super-resolution optimization 24

Dense object detection for remote sensing images based on mu...

引用

3rd International Conference on Signal Processing, Computer Networks and Communications, SPCNC 2024

作者： Li, Lu Zhu, Xia Ni, Shaofeng Gao, Fan State Grid Location based Service Co. Ltd. Beijing China State Grid Information & Telecommunication Group Co. Ltd. Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (纸本)9798400710834

Detecting dense objects in remote sensing image is a critical yet challenging task due to variations in target scale, image resolution, and complex backgrounds. Traditional detection methods often struggle with these dense regions, particularly for small or overlapping objects. To overcome these limitations, this study introduces an innovative approach that combines multi-scale partitioning with super-resolution optimization to improve the detection of densely packed objects. By applying K-Means clustering to identify regions of interest (ROI) and using a local super-resolution network to enhance these areas, we improve the clarity and detectability of small-scale objects. Additionally, we implement a global-local feature extraction architecture, where global features are captured using Transformer-based attention, while local features focus on fine-grained object details. Non-Maximum Suppression (NMS) is employed to fuse multi-scale features and eliminate redundant detections. Experimental results on the DOTA and HRSC2016 datasets demonstrate the effectiveness of our approach, achieving superior performance over state-of-the-art methods in detecting small and densely packed targets. This method shows significant promise for remote sensing applications requiring high-precision target detection. © 2024 Copyright held by the owner/author(s).

关键词： Proximity sensors

来源：评论

学校读者我要写书评

暂无评论

Exploring the Overall Stiffness Distribution Law of Weakly Rigid Composite Fairings 7th

Exploring the Overall Stiffness Distribution Law of Weakly R...

引用

7th China Aeronautical Science and technology Conference, CASTC 2024

作者： Yin, Rongying Kong, Chuifeng Dong, Yushuang Ma, Jichuan Gao, Hanjun Harbin Hafei Aviation Industry Co Ltd Harbin150060 China School of Mechanical Engineering and Automation State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China School of Technology Forestry University Beijing100083 China

ISBN: (纸本)9789819797677

To elucidate the stresses and deformations occurring during the assembly of the powerhouse fairing, finite element analysis (ABAQUS) was employed to emulate the assembly process. A numerical simulation model was constructed for the assembly process of the weakly rigid composite fairing by digitizing its geometry, material properties, and the forces exerted during assembly. Initially, the geometric data and material parameters of the fairing were meticulously collected and analyzed, considering its weakly rigid composite material properties. Subsequently, the finite element analysis method was utilized to partition the fairing’s geometry into minute regions, thereby establishing a numerical simulation model of the fairing assembly process. During the simulation, various forces acting on the fairing during assembly, such as the binding force of the assembly fixture and mechanical loads, were taken into account. The stress and deformation distributions during the fairing assembly process were derived through numerical simulation of the model. The findings indicate that the overall stiffness distribution law of the weakly rigid composite fairing can be summarized as follows: larger fixed boundaries, smaller applied forces, more rigid materials, and more intricate geometries enhance the overall stiffness of the fairing. © Chinese Society of Aeronautics and Astronautics 2025.

关键词： ABAQUS

来源：评论

学校读者我要写书评

暂无评论

GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object Generation

arXiv

引用

arXiv 2025年

作者： Tao, Ye Zhang, Jiawei Shi, Yahao Zou, Dongqing Zhou, Bin State Key Laboratory of Virtual Reality Technology and Systems Beihang University China SenseTime Research China PBVR

Image-based 3D generation has vast applications in robotics and gaming, where high-quality, diverse outputs and consistent 3D representations are crucial. However, existing methods have limitations: 3D diffusion models are limited by dataset scarcity and the absence of strong pre-trained priors, while 2D diffusion-based approaches struggle with geometric consistency. We propose a method that leverages 2D diffusion models’ implicit 3D reasoning ability while ensuring 3D consistency via Gaussian-splatting-based geometric distillation. Specifically, the proposed Gaussian Splatting Decoder enforces 3D consistency by transforming SV3D latent outputs into an explicit 3D representation. Unlike SV3D, which only relies on implicit 2D representations for video generation, Gaussian Splatting explicitly encodes spatial and appearance attributes, enabling multi-view consistency through geometric constraints. These constraints correct view inconsistencies, ensuring robust geometric consistency. As a result, our approach simultaneously generates high-quality, multi-viewconsistent images and accurate 3D models, providing a scalable solution for single-image-based 3D generation and bridging the gap between 2D Diffusion diversity and 3D structural coherence. Experimental results demonstrate state-of-the-art multi-view consistency and strong generalization across diverse datasets. The code will be made publicly available upon acceptance. © 2025, CC BY.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

CAFE-TALK: GENERATING 3D TALKING FACE ANIMATION WITH MULTIMODAL COARSE- AND FINE-GRAINED CONTROL

arXiv

引用

arXiv 2025年

作者： Chen, Hejia Zhang, Haoxian Zhang, Shoulong Liu, Xiaoqiang Zhuang, Sisi Zhang, Yuan Wan, Pengfei Zhang, Di Li, Shuai State Key Laboratory of Virtual Reality Systems and Technology Beihang University China Kuaishou Technology China Zhongguancun Laboratory China

Speech-driven 3D talking face method should offer both accurate lip synchronization and controllable expressions. Previous methods solely adopt discrete emotion labels to globally control expressions throughout sequences while limiting flexible fine-grained facial control within the spatiotemporal domain. We propose a diffusion-transformer-based 3D talking face generation model, Cafe-Talk, which simultaneously incorporates coarse- and fine-grained multimodal control conditions. Nevertheless, the entanglement of multiple conditions challenges achieving satisfying performance. To disentangle speech audio and fine-grained conditions, we employ a two-stage training pipeline. Specifically, Cafe-Talk is initially trained using only speech audio and coarse-grained conditions. Then, a proposed fine-grained control adapter gradually adds fine-grained instructions represented by action units (AUs), preventing unfavorable speech-lip synchronization. To disentangle coarse- and fine-grained conditions, we design a swap-label training mechanism, which enables the dominance of the fine-grained conditions. We also devise a mask-based CFG technique to regulate the occurrence and intensity of fine-grained control. In addition, a text-based detector is introduced with text-AU alignment to enable natural language user input and further support multimodal control. Extensive experimental results prove that Cafe-Talk achieves state-of-the-art lip synchronization and expressiveness performance and receives wide acceptance in fine-grained control in user studies. Project page: https://***/cafe-talk/ © 2025, CC BY.

关键词： Coarse-grained modeling

来源：评论

学校读者我要写书评

暂无评论

Refining Boundary Sample Space for Differentiable Rendering 16

Refining Boundary Sample Space for Differentiable Rendering

引用

2024 16th International Conference on Graphics and Image Processing, ICGIP 2024

作者： Gao, Ruicheng Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Jingdezhen Research Institute Beihang University Jingdezhen333000 China Qingdao Research Institute Beihang University Qingdao266104 China

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

The objective of physics-based differentiable rendering (PBDR) is to propagate gradients between scene parameters and the intensities of image pixels in a manner that is physically correct. The gradients obtained can be applied in optimization algorithms for the reconstruction of 3D geometry or materials, or they can be further propagated into neural network to learn neural representations of the scene. However, applying automatic differentiation techniques directly to the primary rendering process will result in biased gradients, as the rendering integral contains moving high-dimensional discontinuities. Based on how these discontinuities are managed-either implicitly or explicitly-existing PBDR methods can be categorized into two groups: reparameterization methods and boundary sampling methods. Boundary sampling methods need to construct paths that have one segment tangent to the geometry being differentiated in order to estimate a boundary integral to address the discontinuities explicitly. Such paths are usually constructed by sampling the tangent segment first and then extending it to complete the paths for subsequent processing. Fortunately, the number of dimensions in the space composed of such tangent segments is only three. In scenes comprised solely of triangle meshes, the first dimension is used to parameterize all the edges on the mesh, which determines a point on the tangent segment. The remaining two dimensions are used to parameterize the direction of the tangent segment. However, state-of-the-art boundary sampling methods parameterize the first dimension uniformly, which is inefficient because only a small portion of the edges contributes to the boundary integral, resulting in wasted parameter space. In this paper, we parameterize the first dimension by considering both edge length and contributions, thereby allocating more parameter space to important edges. Experiments demonstrate that our methods achieve lower variance gradients in the forward dif

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Research on ABAQUS-Based Fairing Mechanical Specimen Modeling and Mechanical Properties 7th

Research on ABAQUS-Based Fairing Mechanical Specimen Modelin...

引用

7th China Aeronautical Science and technology Conference, CASTC 2024

作者： Dong, Yushuang Yin, Rongying Xin, Yuhan Yang, Shangru Gao, Hanjun School of Technology Beijing Forestry University Beijing100083 China AVIC HARBN AIRCRAFT INDUSTRY GROUP CO. LTD Harbin150060 China State Key Laboratory of Virtual Reality Technology and Systems School of Mechanical Engineering and Automation Beihang University Beijing100191 China

ISBN: (纸本)9789819797646

To deeply study the mechanical properties of the fairing, the mechanically cut specimens of the fairing were modeled and simulated using ABAQUS 6.14 finite element software. By establishing the geometry of the fairing mechanical specimens, the stress–strain response and deformation characteristics of six mechanical specimens under different loading conditions were simulated and analyzed. The results show the differences in the mechanical properties of the fairing specimens with two different materials, Notably, when aramid paper honeycomb material was juxtaposed with high-temperature fireproof cloth material, the former exhibited superior load-bearing capacity and robustness. In addition, the mechanical properties of the fairing were further investigated in depth by comparing the mechanical responses of the specimens under different gradient forces. © Chinese Society of Aeronautics and Astronautics 2025.

关键词： ABAQUS

来源：评论

学校读者我要写书评

暂无评论

Passive activity enhances residual control ability in patients with complete spinal cord injury

引用

Neural Regeneration Research 2025年第8期20卷 2337-2347页

作者： Yanqing Xiao Mingming Gao Zejia He Jia Zheng Hongming Bai Jia-Sheng Rao Guiyun Song Wei Song Xiaoguang Li Beijing Key Laboratory for Biomaterials and Neural Regeneration Beijing Advanced Innovation Center for Biomedical EngineeringSchool of Biological Science and Medical EngineeringBeihang UniversityBeijingChina Department of Rehabilitation Evaluation China Rehabilitation Research CenterBeijingChina Cardiac Center Beijing Children’s HospitalCapital Medical UniversityBeijingChina The State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijingChina Department of Rehabilitation Engineering China Rehabilitation Science InstituteBeijingChina

Patients with complete spinal cord injury retain the potential for volitional muscle activity in muscles located below the spinal injury ***,because of prolonged inactivity,initial attempts to activate these muscles may not effectively engage any of the remaining neurons in the descending pathway.A previous study unexpectedly found that a brief clinical round of passive activity significantly increased volitional muscle activation,as measured by surface *** this study,we further explored the effect of passive activity on surface electromyographic signals during volitional control tasks among individuals with complete spinal cord *** patients with chronic complete thoracic spinal cord injury were *** electromyography data from eight major leg muscles were acquired and compared before and after the passive activity *** results indicated that the passive activity led to an increased number of activated volitional muscles and an increased frequency of *** the cumulative root mean square of surface electromyography amplitude for volitional control of movement showed a slight increase after passive activity,the difference was not statistically *** findings suggest that brief passive activity may enhance the ability to initiate volitional muscle activity during surface electromyography tasks and underscore the potential of passive activity for improving residual motor control among patients with motor complete spinal cord injury.

关键词： complete spinal cord injury cycle training epidural electrical stimulation motor training passive activity physiological state spinal cord circuit surface electromyography volitional control task

来源：评论

学校读者我要写书评

暂无评论

SSCCPC-Net: Simultaneously Learning 2D and 3D Features with CLIP for Semantic Scene Completion on Point Cloud 41st

SSCCPC-Net: Simultaneously Learning 2D and 3D Features with...

引用

41st Computer Graphics International Conference, CGI 2024

作者： Duan, Wantong Bao, Yongtang Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Shandong University of Science and Technology Qingdao266590 China Jingdezhen Research Institute of Beihang University Jingdezhen333000 China Qingdao Research Institute of Beihang University Qingdao266000 China

ISBN: (纸本)9783031820236

Compare to traditional Scene Completion (SC), Semantic Scene Completion (SSC) is a challenging task that aims to generate complete and semantically consistent 3D scene from partial and sparse input data, which is fundamental to fully understanding the scene and being able to interact with it. Consequently, the SSC task has received much attention in recent years. Most of the methods are voxel-based approaches, but they have high computational and memory requirements. A few works based on point cloud do not sufficiently exploit the correlation between semantic segmentation and geometric completion subtasks, while focusing too much on point cloud shape features and ignoring the rich texture information that RGB images can provide. In this paper, we present SSCCPC-Net (Semantic Scene Completion with CLIP on Point Cloud-Net), a novel network architecture for point cloud semantic scene completion using a combination of 2D and 3D features. Inspired by recent works of large pretrained vision-language models in semantic segmentation, we explore to accomplish SSC task with the help of Contrastive Language-Image Pre-Training (CLIP) model. Specifically, we use the CLIP features for guidance to fuse the 2D features extracted from the RGB image and the 3D features extracted from the point cloud. The fused features are then fed into our designed Semantic-Completion Decoder for per-point semantic prediction and semantic labeling-assisted point cloud completion. Finally, we obtain the complete semantically point cloud. Numerous experiments have demonstrated that our method has higher effectiveness and generalizability compared to state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：