检索结果-内蒙古大学图书馆

Zero-Shot Image Harmonization with Generative Model Prior

IEEE Transactions on Multimedia 2025年

作者： Chen, Jianqi Zhang, Yilan Zou, Zhengxia Chen, keyan Shi, Zhenwei Beihang University Image Processing Center School of Astronautics Beijing100191 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Astronautics Beijing100191 China Beihang University Department of Guidance Navigation and Control School of Astronautics Beijing100191 China

We propose a zero-shot approach to image harmonization, aiming to overcome the reliance on large amounts of synthetic composite images in existing methods. These methods, while showing promising results, involve significant training expenses and often struggle with generalization to unseen images. To this end, we introduce a fully modularized framework inspired by human behavior. Leveraging the reasoning capabilities of recent foundation models in language and vision, our approach comprises three main stages. Initially, we employ a pretrained vision-language model (VLM) to generate descriptions for the composite image. Subsequently, these descriptions guide the foreground harmonization direction of a text-to-image generative model (T2I). We refine text embeddings for enhanced representation of imaging conditions and employ self-attention and edge maps for structure preservation. Following each harmonization iteration, an evaluator determines whether to conclude or modify the harmonization direction. The resulting framework, mirroring human behavior, achieves harmonious results without the need for extensive training. We present compelling visual results across diverse scenes and objects, along with quantitative comparisons validating the effectiveness of our approach. Our code is available at https://***/WindVChen/Diff-Harmonization. © 1999-2012 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Audio-visual aware Foveated Rendering

引用

IEEE Transactions on Visualization and Computer Graphics 2025年 PP卷 PP页

作者： Shi, Xuehuai Li, Yucheng Li, Jiaheng Wu, Jian Yin, Jieming Chen, Xiaobai Wang, Lili Nanjing University of Posts and Telecommunications School of Computer Science Jiangsu 210023 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University School of Computer Science and Engineering Beijing100191 China

With the increasing complexity of geometry and rendering effects in virtual reality (VR) scenes, existing foveated rendering methods for VR head-mounted displays (HMDs) struggle to meet users' demands for VR scene rendering with high frame rates (≥ 60 f ps for rendering binocular foveated images in VR scenes containing over 50M triangles). Current research validates that auditory content affects the perception of the human visual system (HVS). However, existing foveated rendering methods primarily model the HVS's eccentricity-dependent visual perception ability on the visual content in VR while ignoring the impact of auditory content on the HVS's visual perception. In this paper, we introduce an auditory-content-based perceived rendering quality analysis to quantify the impact of visual perception under different auditory conditions in foveated rendering. Based on the analysis results, we propose an audio-visual aware foveated rendering method (AvFR). AvFR first constructs an audio-visual feature-driven perception model that predicts the eccentricity-based visual perception in real time by combining the scene's audio-visual content, and then proposes a foveated rendering cost optimization algorithm to adaptively control the shading rate of different regions with the guidance of the perception model. In complex scenes with visual and auditory content containing over 1.17M triangles, AvFR renders high-quality binocular foveated images at an average frame rate of 116 f ps. The results of the main user study and performance evaluation validate that AvFR achieves significant performance improvement (up to 1.4× speedup) without lowering the perceived visual quality compared with the state-of-the-art VR-HMD foveated rendering method. © 1995-2012 IEEE.

关键词： Foveated Rendering Perception-driven Rendering virtual reality

来源：评论

学校读者我要写书评

暂无评论

CR-Famba: A Frequency-Domain Assisted Mamba for Thin Cloud Removal in Optical Remote Sensing Imagery

引用

IEEE Transactions on Multimedia 2025年

作者： Liu, Jiao Pan, Bin Shi, Zhenwei Nankai University TKLNDST College of Computer Science Tianjin300350 China Nankai University School of Statistics and Data Science KLMDASR LEBPS LPMC Tianjin300071 China Beihang University Image Processing Center School of Astronautics the State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China

Optical remote sensing images are inevitably affected by cloud cover. To remove clouds from optical remote sensing images, a series of deep learning-based thin cloud removal methods have been developed. However, these methods have not explored the long-range modeling ability of state space models in optical remote sensing image thin cloud removal. In this paper, we propose a frequency-domain assisted Mamba for thin cloud removal, which is called CR-Famba. In CR-Famba, to better extract global and local features of images, we design a frequency-domain assisted state space layer (FDA-SSL). The FDA-SSL consists of two core components: residual state space block (RSSB) and frequency domain detail enhancement block (FDDEB). The RSSB utilizes the visual state space module (VSSM) to extract long-range dependencies of images from a spatial perspective while adding convolutional layers to overcome local pixel forgetting. Due to the rich detailed information of remote sensing images, we present FDDEB equipped with discrete wavelet transform (DWT) to supplement the extracted local information from the frequency domain perspective. We conduct experiments on different types of cloud-containing datasets, and the results show that our method can recover images with clearer texture details compared to other methods. https://***/lab-PANbin/ © 2025 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Morphology and Volume Estimation of the Amniotic Sac Based on MRI Image Analysis: Construction of a Knowledge Graph for Risk Assessment of Premature Rupture of Membranes

SSRN

引用

SSRN 2025年

作者： Zhang, Tong Zhang, Yan Li, Shuai Cheng, Yongfeng Xiao, Yuntian Zhao, Zilong Institute of Solid Mechanics School of Aeronautics Sciences and Engineering Beihang University Beijing100083 China Obstetrics and Gynecology Department Peking University Third Hospital Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

Achieving the quantification of the amniotic sac's volume and the visualization of its morphology provides a starting point for constructing the PROM knowledge ***, the Magnetic Resonance Imaging (MRI) scan data is imported into the Segment Anything Model (SAM), where region segmentation is performed through semi-automatic point selection. Through volume visualization, a high-resolution, voxel-based 3D reconstruction of the amniotic membrane with a smooth surface is obtained. The high-fidelity surface shape of the amniotic membrane can be well observed by the visualization of voxel data. An edge detection algorithm is applied, voxel integration is used to calculate an approximate digital volume of the amniotic sac. Finally, mathematical methods and techniques are applied to the identified edge curves to establish a semi-empirical formula for estimating the volume of the amniotic sac. Five approximate digital volumes were calculated using the SAM and considered as reference values. A comparison of the results from the semi-empirical formula with the reference values reveals a maximum error rate of 14%, a minimum error rate of 6%, and an average error rate of 10%. These results highlight the high accuracy, simplicity, and efficiency of the semi-empirical formula. Furthermore, a high-level hierarchical framework for constructing the risk assessment knowledge graph of PROM is proposed. Develop a multi-hierarchical knowledge graph framework for assessing the risk of premature rupture of membranes, offering both theoretical support and technical assurance for personalized risk evaluation, data-driven decision-making, systematic diagnostic and treatment processes, and visualized analysis. This will foster the precision, standardization, and intelligent application of clinical practices. © 2025, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

UNeLF: Unconstrained Neural Light Field for Self-Supervised Angular Super-Resolution

引用

IEEE Transactions on Circuits and systems for Video technology 2025年

作者： Zhao, Mingyuan Sheng, Hao Chen, Rongshan Cong, Ruixuan Cui, Zhenglong Yang, Da Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Data Science and Intelligent Computing Laboratory Hangzhou International Innovation Institute Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

Compared to supervised learning methods, self-supervised learning methods address the domain gap problem between light field (LF) datasets collected under varying acquisition conditions, which typically leads to decreased performance when differences exist in the distribution between the training and test sets. However, current self-supervised light field angular super-resolution (LFASR) techniques primarily focus on exploiting discrete spatial-angular features while neglecting continuous LF information. In contrast to previous work, we propose a self-supervised unconstrained neural light field (UNeLF) to continuously represent LF for LFASR. Specifically, any LF can be described as the camera pose for each sub-aperture image (SAI) and the two-plane that captures these SAIs. To describe the former, we introduce a SAIs-dependent pose optimization method to solve the issue that arises from the narrow baseline of most LF data, which hinders robust camera pose estimation. This mechanism reduces the number of trainable camera parameters from a quadratic to a constant scale, thereby alleviating the complexity of joint optimization. For the latter, we propose a novel adaptive two-plane parameterization strategy to determine the two-plane that captures these SAIs, facilitating refocusing. Finally, we jointly optimize the camera parameters, near-far planes and neural light field, efficiently mapping each adaptive two-plane parameterized ray to its correspondence color in a continuous manner. Comprehensive experiments demonstrate that UNeLF achieves faster training and inference with fewer computational resources while exhibiting superior performance on both synthetic and real-world datasets. © 1991-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation

arXiv

引用

arXiv 2025年

作者： Zhang, Zongye Cai, Wenrui Liu, Qingjie Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

While current skeleton action recognition models demonstrate impressive performance on large-scale datasets, their adaptation to new application scenarios remains challenging. These challenges are particularly pronounced when facing new action categories, diverse performers, and varied skeleton layouts, leading to significant performance degeneration. Additionally, the high cost and difficulty of collecting skeleton data make large-scale data collection impractical. This paper studies one-shot and limited-scale learning settings to enable efficient adaptation with minimal data. Existing approaches often overlook the rich mutual information between labeled samples, resulting in sub-optimal performance in low-data scenarios. To boost the utility of labeled data, we identify the variability among performers and the commonality within each action as two key attributes. We present SkeletonX, a lightweight training pipeline that integrates seamlessly with existing GCN-based skeleton action recognizers, promoting effective training under limited labeled data. First, we propose a tailored sample pair construction strategy on two key attributes to form and aggregate sample pairs. Next, we develop a concise and effective feature aggregation module to process these pairs. Extensive experiments are conducted on NTU RGB+D, NTU RGB+D 120, and PKU-MMD with various GCN backbones, demonstrating that the pipeline effectively improves performance when trained from scratch with limited data. Moreover, it surpasses previous state-of-the-art methods in the one-shot setting, with only 1/10 of the parameters and much fewer FLOPs. The code and data are available at: https://***/zzysteve/SkeletonX Copyright © 2025, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Mamba-based deformable medical image registration with an annotated brain MR-CT dataset

引用

Computerized Medical Imaging and Graphics 2025年 123卷 102566-102566页

作者： Wang, Yinuo Guo, Tao Yuan, Weimin Shu, Shihao Meng, Cai Bai, Xiangzhi Image Processing Center Beihang University Beijing100191 China Thuwal23955-6900 Saudi Arabia State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technology Ministry of Education Beijing100191 China Vision-BHU Joint AI+Computing Optics Laboratory Beijing100191 China

Deformable registration is essential in medical image analysis, especially for handling various multi- and mono-modal registration tasks in neuroimaging. Existing studies lack exploration of brain MR-CT registration, and face challenges in both accuracy and efficiency improvements of learning-based methods. To enlarge the practice of multi-modal registration in brain, we present SR-Reg, a new benchmark dataset comprising 180 volumetric paired MR-CT images and annotated anatomical regions. Building on this foundation, we introduce MambaMorph, a novel deformable registration network based on an efficient state space model Mamba for global feature learning, with a fine-grained feature extractor for low-level embedding. Experimental results demonstrate that MambaMorph surpasses advanced ConvNet-based and Transformer-based networks across several multi- and mono-modal tasks, showcasing impressive enhancements of efficacy and efficiency. Code and dataset are available at https://***/mileswyn/MambaMorph. © 2025 Elsevier Ltd

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Light Space Cascaded Shadow Maps Algorithm for Real Time Rendering

引用

Journal of Computer Science & technology 2011年第1期26卷 176-186页

作者：梁晓辉马上岑丽霞于卓 State Key Lab.of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang University

Owing to its generality and efficiency, Cascaded Shadow Maps （CSMs） has an important role in real-time shadow rendering in large scale and complex virtual environments. However, CSMs suffers from redundant rendering problem -- objects are rendered undesirably to different shadow map textures when view direction and light direction are not perpendicular. In this paper, we present a light space cascaded shadow maps algorithm. The algorithm splits a scene into non-intersecting layers in light space, and generates one shadow map for each layer through irregular frustum clipping and scene organization, ensuring that any shadow sample point never appears in multiple shadow maps. A succinct shadow determination method is given to choose the optimal shadow map when rendering scenes. We also combine the algorithm with stable cascaded shadow maps and soft shadow algorithm to avoid shadow flicking and produce soft shadows. The results show that the algorithm effectively improves the efficiency and shadow quality of CSMs by avoiding redundant rendering, and can produce high-quality shadow rendering in large scale dynamic environments with real-time performance.

关键词： shadow mapping light space redundant rendering large scale dynamic environments

来源：评论

学校读者我要写书评

暂无评论

Towards Depth-continuous Scene Representation with Displacement Field for Robust Light Field Depth Estimation

引用

IEEE Transactions on Multimedia 2025年

作者： Chen, Rongshan Sheng, Hao Yang, Da Cong, Ruixuan Cui, Zhenglong Wang, Sizhe Wang, Tun Zhao, Mingyuan Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Key Laboratory of Data Science and Intelligent Computing International Innovation Institute 166 Shuanghongqiao Street Pingyao Town Yuhang District Hangzhou31 1115 China Macao Polytechnic University Faculty of Applied Sciences Macao999078 China

The light field (LF) captures both the spatial and angular information of scenes, enabling accurate depth estimation. However, previous deep learning methods typically model surface depth only while ignoring the continuous nature of depth in 3D scenes. In this paper, we use the displacement field (DF) to describe this continuous property, and propose a novel depth-continuous scene representation for robust LF depth estimation. Experiments demonstrate that our representation enables the network to generate highly detailed depth maps with fewer parameters and faster speeds. Specifically, inspired by the signed distance field in 3D object descriptions, we aim to exploit the intrinsic depth-continuous property of 3D scenes via DF and define a novel depth-continuous scene representation. Then, we introduce a simple, yet general, learning framework for depth-continuous scene embedding, and the proposed network, DepthDF, achieves state-of-the-art performance on both synthetic and real-world LF datasets, ranking 1st on the HCI 4D light field benchmark. Furthermore, previous LF depth estimation methods can also be seamlessly integrated into this framework. Finally, we extend this framework beyond LF depth estimation to various tasks, including multiview stereo depth inference, LF superresolution, and LF salient object detection. Our experiments demonstrate an improved performance when continuous scene representation is applied, suggesting that our framework can potentially provide insights for more fields. © 1999-2012 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Biologically adaptive robust mean shift algorithm with Cauchy predator-prey BBO and space variant resolution for unmanned helicopter formation

引用

Science China(Information Sciences) 2014年第11期57卷 195-207页

作者： WANG XiaoHua DUAN HaiBin State Key Laboratory of Virtual Reality Technology and Systems Beihang University

Visual tracking technology can provide measurement information for unmanned helicopter formation and thus, more attention is being paid to this research area. We propose a novel mean shift(MS) algorithm that is both adaptive and robust for unmanned helicopter formation and apply it to the leading unmanned helicopter tracking. The movement of an unmanned helicopter is very flexible and changeable, which makes the tracking there of more difficulty than for common targets. In creating an algorithm that can adapt to the acceleration of the unmanned helicopter and estimates both the scale and orientation of the movement changes, we combine the traditional MS with the bio-inspired Cauchy predator-prey biogeography-based optimization(CPPBBO)evolutionary algorithm, and also the space variant resolution(SVR) mechanism of the human visual system(MS-CPPBBO-SVR). To demonstrate the effectiveness and robustness of the proposed method and justify the importance of the CPPBBO algorithm and SVR mechanism at the same time, a series of comparative experiments were carried out. The experimental results of the proposed MS-CPPBBO-SVR method are compared with other competitive tracking methods, such as MS, MS with SVR(MS-SVR), MS-SVR with several other optimization algorithms, and the robust particle filter algorithm. The experimental results demonstrate that our proposed tracking approach, MS-CPPBBO-SVR, is more adaptive, robust and efficient in target tracking than the other methods.

关键词： unmanned helicopter formation tracking mean shift biogeography-based optimization(BBO) predator-prey space variant resolution(SVR)

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：