检索结果-内蒙古大学图书馆

GarVerseLOD: High-Fidelity 3D Garment Reconstruction from a Single In-the-Wild image using a Dataset with Levels of Details

引用

ACM TRANSACTIONS ON GRAPHICS 2024年第6期43卷 1-12页

作者： Luo, Zhongjin Liu, Haolin Li, Chenghong Du, Wanghao Jin, Zirong Sun, Wanhu Nie, Yinyu Chen, Weikai Han, Xiaoguang CUHKSZ SSE Shenzhen Peoples R China CUHKSZ FNii Shenzhen Peoples R China Huawei Noahs Ark Lab London England Tencent Games DCC Algorithm Res Ctr Palo Alto CA USA

Neural implicit functions have brought impressive advances to the state-ofthe-art of clothed human digitization from multiple or even single images. However, despite the progress, current arts still have difficulty generalizing to unseen images with complex cloth deformation and body poses. In this work, we present GarVerseLOD, a new dataset and framework that paves the way to achieving unprecedented robustness in high-fidelity 3D garment reconstruction from a single unconstrained image. Inspired by the recent success of large generative models, we believe that one key to addressing the generalization challenge lies in the quantity and quality of 3D garment data. Towards this end, GarVerseLOD collects 6,000 high-quality cloth models with fine-grained geometry details manually created by professional artists. In addition to the scale of training data, we observe that having disentangled granularities of geometry can play an important role in boosting the generalization capability and inference accuracy of the learned model. We hence craft GarVerseLOD as a hierarchical dataset with levels of details (LOD), spanning from detail-free stylized shape to pose-blended garment with pixel-aligned details. This allows us to make this highly under- constrained problem tractable by factorizing the inference into easier tasks, each narrowed down with smaller searching space. To ensure GarVerseLOD can generalize well to in-the-wild images, we propose a novel labeling paradigm based on conditional diffusion models to generate extensive paired images for each garment model with high photorealism. We evaluate our method on a massive amount of in-the-wild images. Experimental results demonstrate that GarVerseLOD can generate standalone garment pieces with significantly better quality than prior approaches while being robust against a large variation of pose, illumination, occlusion, and deformation. Code and dataset are available at ***.

关键词： image-based modeling 3D Garment Reconstruction 3D Garment Dataset

来源：评论

学校读者我要写书评

暂无评论

Precision non-invasive brain stimulation: an in silico pipeline for personalized control of brain dynamics

引用

JOURNAL OF NEURAL ENGINEERING 2025年第2期22卷 2025 Feb 20页

作者： Karimi, Fariba Steiner, Melanie Newton, Taylor Lloyd, Bryn A. Cassara, Antonino M. de Fontenay, Paul Farcito, Silvia Triebkorn, Jan Paul Beanato, Elena Wang, Huifang Iavarone, Elisabetta Hummel, Friedhelm C. Kuster, Niels Jirsa, Viktor Neufeld, Esra Fdn Res Informat Technol Soc ITIS Zurich Switzerland Swiss Fed Inst Technol Dept Informat Technol & Elect Engn Zurich Switzerland Inst Neurosci Syst Marseille France Swiss Fed Inst Technol EPFL Defitech Chair Clin Neuroengn Ctr Neuroprosthet CNP Geneva Switzerland Swiss Fed Inst Technol EPFL Brain Mind Inst BMI Geneva Switzerland Swiss Fed Inst Technol EPFL Valais Defitech Chair Clin Neuroengn Ctr Neuroprosthet CNP Clin Romande Readaptat Sion Switzerland Swiss Fed Inst Technol EPFL Valais Brain Mind Inst BMI Clin Romande Readaptat Sion Switzerland Univ Geneva Med Sch Clin Neurosci Geneva Switzerland

Objective. Non-invasive brain stimulation (NIBS) offers therapeutic benefits for various brain disorders. Personalization may enhance these benefits by optimizing stimulation parameters for individual subjects. Approach. We present a computational pipeline for simulating and assessing the effects of NIBS using personalized, large-scale brain network activity models. Using structural MRI and diffusion-weighted imaging data, the pipeline leverages a convolutional neural network-based segmentation algorithm to generate subject-specific head models with up to 40 tissue types and personalized dielectric properties. We integrate electromagnetic simulations of NIBS exposure with whole-brain network models to predict NIBS-dependent perturbations in brain dynamics, simulate the resulting EEG traces, and quantify metrics of brain dynamics. Main results. The pipeline is implemented on o2S2PARC, an open, cloud-based infrastructure designed for collaborative and reproducible computational life science. Furthermore, a dedicated planning tool provides guidance for optimizing electrode placements for transcranial temporal interference stimulation. In two proof-of-concept applications, we demonstrate that: (i) transcranial alternating current stimulation produces expected shifts in the EEG spectral response, and (ii) simulated baseline network activity exhibits physiologically plausible fluctuations in inter-hemispheric synchronization. Significance. This pipeline facilitates a shift from exposure-based to response-driven optimization of NIBS, supporting new stimulation paradigms that steer brain dynamics towards desired activity patterns in a controlled manner.

关键词： non-invasive brain stimulation whole brain network modeling image-based modeling personalized stimulation planning response-driven neuromodulation

来源：评论

学校读者我要写书评

暂无评论

Challenges in modeling Hemodynamics in Cerebral Aneurysms Related to Arteriovenous Malformations

引用

CARDIOVASCULAR ENGINEERING AND TECHNOLOGY 2022年第5期13卷 673-684页

作者： Boster, Kimberly A. Stevens Shidhore, Tanmay C. Cohen-Gadol, Aaron A. Christov, Ivan C. Rayz, Vitaliy L. Purdue Univ Sch Mech Engn W Lafayette IN 47907 USA Indiana Univ Sch Med Dept Neurol Surg Indianapolis IN 46202 USA Purdue Univ Weldon Sch Biomed Engn Sch Mech Engn W Lafayette IN 47907 USA

Purpose The significantly higher incidence of aneurysms in patients with arteriovenous malformations (AVMs) suggests a strong hemodynamic relationship between these lesions. The presence of an AVM alters hemodynamics in proximal vessels by drastically changing the distal resistance, thus affecting intra-aneurysmal flow. This study discusses the challenges associated with patient-specific modeling of aneurysms in the presence of AVMs. Methods We explore how the presence of a generic distal AVM affects upstream aneurysms by examining the relationship between distal resistance and aneurysmal wall shear stress using physiologically realistic estimates for the influence of the AVM on hemodynamics. Using image-based computational models of aneurysms and surrounding vasculature, aneurysmal wall-shear stress is calculated for a range of distal resistances corresponding to the presence of AVMs of various sizes and compared with a control case representing the absence of an AVM. Results In the patient cases considered, the alteration in aneurysmal wall shear stress due to the presence of an AVM is considerable, as much as 19 times the base case wall shear stress. Furthermore, the relationship between aneurysmal wall shear stress and distal resistance is shown to be highly geometry-dependent and nonlinear. In most cases, the range of physiologically realistic possibilities for AVM-related distal resistance are so large that patient-specific flow measurements are necessary for meaningful predictions of wall shear stress. Conclusions The presented work offers insight on the impact of distal AVMs on aneurysmal wall shear stress using physiologically realistic computational models. Patient-specific modeling of hemodynamics in aneurysms and associated AVMs has great potential for understanding lesion pathogenesis, surgical planning, and assessing the effect of treatment of one lesion relative to another. However, we show that modeling approaches cannot usually meaningfully quantify

关键词： image-based modeling Cerebrovascular hemodynamics Arteriovenous malformations Cerebral aneurysms

来源：评论

学校读者我要写书评

暂无评论

Verification Study of In Silico Computed Intracardiac Blood Flow With 4D Flow MRI

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2024年第9期71卷 2568-2579页

作者： Obermeier, L. Wiegand, M. Hellmeier, F. Manini, C. Kuehne, T. Goubergrits, L. Vellguth, K. Inst Comp assisted Cardiovasc Med Deutsch Herzzentrumder Charite D-13353 Berlin Germany Charite Univ med Berlin D-10117 Berlin Germany Free Univ Berlin D-10117 Berlin Germany Humboldt Univ D-10117 Berlin Germany German Ctr Cardiovasc Res DZHK Berlin Germany Einstein Ctr Digital Future Berlin Germany

Objective: Major challenges for clinical applications of in silico medicine are limitations in time and computational resources. Computational approaches should therefore be tailored to specific applications with relatively low complexity and must be verified and validated against clinical gold standards. Methods: This study performed computational fluid dynamics simulations of left ventricular hemodynamics of different complexity based on shape reconstruction from steady state gradient echo magnetic resonance imaging (MRI) data. Computed flow results of a rigid wall model (RWM) and a prescribed motion fluid-structure interaction (PM-FSI) model were compared against phase-contrast MRI measurements for three healthy subjects. Results: Extracted boundary conditions from the steady state MRI sequences as well as computed metrics, such as flow rate, valve velocities, and kinetic energy show good agreement with in vivo flow measurements. Regional flow analysis reveals larger differences. Conclusion: Basic flow structures are well captured with RWM and PM-FSI. For the computation of further biomarkers like washout or flow efficiency, usage of PM-FSI is required. Regarding boundary-near flow, more accurate anatomical models are inevitable. Significance: These results delineate areas of application of both methods and lay a foundation for larger validation studies and sensitivity analysis for healthy and diseased cases, being an essential step upon clinical translations.

关键词： Magnetic resonance imaging Shape image reconstruction Computational modeling Valves Steady-state Biomedical engineering Computational fluid dynamics hemodynamics image-based modeling in silico medicine mitral valve verification 4D flow MRI

来源：评论

学校读者我要写书评

暂无评论

Pano2Room: Novel View Synthesis from a Single Indoor Panorama 24

Pano2Room: Novel View Synthesis from a Single Indoor Panoram...

引用

2024 SIGGRAPH Asia Conference

作者： Pu, Guo Zhao, Yiming Lian, Zhouhui Peking Univ Wangxuan Inst Comp Technol Beijing Peoples R China

ISBN: (纸本)9798400711312

Recent single-view 3D generative methods have made significant advancements by leveraging knowledge distilled from extensive 3D object datasets. However, challenges persist in the synthesis of 3D scenes from a single view, primarily due to the complexity of real-world environments and the limited availability of high-quality prior resources. In this paper, we introduce a novel approach called Pano2Room, designed to automatically reconstruct high-quality 3D indoor scenes from a single panoramic image. These panoramic images can be easily generated using a panoramic RGBD inpainter from captures at a single location with any camera. The key idea is to initially construct a preliminary mesh from the input panorama, and iteratively refine this mesh using a panoramic RGBD inpainter while collecting photo-realistic 3D-consistent pseudo novel views. Finally, the refined mesh is converted into a 3D Gaussian Splatting field and trained with the collected pseudo novel views. This pipeline enables the reconstruction of real-world 3D scenes, even in the presence of large occlusions, and facilitates the synthesis of photo-realistic novel views with detailed geometry. Extensive qualitative and quantitative experiments have been conducted to validate the superiority of our method in single-panorama indoor novel synthesis compared to the state-of-the-art. Our code and data are available at https://***/TrickyGo/Pano2Room.

关键词： image-based Rendering image-based modeling texture synthesis and inpainting

来源：评论

学校读者我要写书评

暂无评论

Do roots need a good haircut for water uptake?

引用

NEW PHYTOLOGIST 2023年第6期240卷 2173-2175页

作者： Boursiac, Yann Bauget, Fabrice Univ Montpellier Inst Plant Sci Montpellier IPSiM Inst Agro CNRSINRAE Montpellier France

This article is a Commentary on Duddek et al. (2023), 240: 2484–2497.

关键词： image-based modeling root hairs root/soil contact water uptake X-ray CT microtomography

来源：评论

学校读者我要写书评

暂无评论

Probing the Role of Multi-scale Heterogeneity in Graphite Electrodes for Extreme Fast Charging

引用

ACS APPLIED MATERIALS & INTERFACES 2022年第16期14卷 18335-18352页

作者： Parmananda, Mukul Norris, Chance Roberts, Scott A. Mukherjee, Partha P. Purdue Univ Sch Mech Engn W Lafayette IN 47907 USA Sandia Natl Labs Engn Sci Ctr Albuquerque NM 87185 USA

Electrode-scale heterogeneity can combine with complex electrochemical interactions to impede lithium-ion battery performance, particularly during fast charging. This study investigates the influence of electrode heterogeneity at different scales on the lithium-ion battery electrochemical performance under operational extremes. We employ image-based mesoscale simulation in conjunction with a three-dimensional electrochemical model to predict performance variability in 14 graphite electrode X-ray computed tomography data sets. Our analysis reveals that the tortuous anisotropy stemming from the variable particle morphology has a dominating influence on the overall cell performance. Cells with platelet morphology achieve lower capacity, higher heat generation rates, and severe plating under extreme fast charge conditions. On the contrary, the heterogeneity due to the active material clustering alone has minimal impact. Our work suggests that manufacturing electrodes with more homogeneous and isotropic particle morphology will improve electrochemical performance and improve safety, enabling electromobility.

关键词： electrode heterogeneity graphite electrodes image-based modeling fast charging lithium plating

来源：评论

学校读者我要写书评

暂无评论

MUNCH: Modelling Unique 'N Controllable Heads 23

MUNCH: Modelling Unique 'N Controllable Heads

引用

15th Annual ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG)

作者： Deb, Debayan Tripathi, Suvidha Puri, Pranit LENS Inc Okemos MI 48864 USA

ISBN: (纸本)9798400703935

The automated generation of 3D human heads has been an intriguing and challenging task for computer vision researchers. Prevailing methods synthesize realistic avatars but with limited control over the diversity and quality of rendered outputs and suffer from limited correlation between shape and texture of the character. We propose a method that offers quality, diversity, control, and realism along with explainable network design, all desirable features to game-design artists in the domain. First, our proposed Geometry Generator identifies disentangled latent directions and generate novel and diverse samples. A Render Map Generator then learns to synthesize multiply high-fidelty physically-based render maps including Albedo, Glossiness, Specular, and Normals. For artists preferring fine-grained control over the output, we introduce a novel Color Transformer Model that allows semantic color control over generated maps. We also introduce quantifiable metrics called Uniqueness and Novelty and a combined metric to test the overall performance of our model. Demo for both shapes & textures can be found: https://munch- ***/. We will release our model along with the synthetic dataset.

关键词： 3D reconstruction image-based modeling Mesh processing Shape analysis Photogrammetry

来源：评论

学校读者我要写书评

暂无评论

SHAPE RECONSTRUCTION OF HERITAGE ASSETS BY POLARIZATION INFORMATION 29

SHAPE RECONSTRUCTION OF HERITAGE ASSETS BY POLARIZATION INFO...

引用

29th CIPA Symposium on Documenting, Understanding, Preserving Cultural Heritage - Humanities and Digital Technologies for Shaping the Future

作者： Xue, Fuduo Filin, Sagi Jin, Weiqi Technion Israel Inst Technol Mapping & Geoinformat Engn Haifa Israel Beijing Inst Technol MOE Key Lab Optoelect Imaging Technol & Syst Beijing Peoples R China

Three-dimensional modeling of heritage assets poses a challenge when high reflectance and featureless surfaces are involved. Because of the complex reflection characteristics, traditional methods, either passive or active, tend to generate noisy and incomplete reconstruction results. To address this, we introduce in this paper a shape-from-polarization system and modeling strategy for the 3-D reconstruction of heritage assets. As demonstrated, by analyzing polarization properties of reflected light, we can generate by a single image pixel-level-resolution normal and depth maps. We consider two system prototypes involving a point light source but different in the polarizing camera configurations. They provide solutions for different reconstruction requirements and acquisition conditions. Our reconstruction model is common however to both involving a closed set of simple computation steps. Our evaluations demonstrate how the proposed method significantly improves the 3-D surface model completeness and level of detail, showing its suitability and value to reach the goal of a high-resolution survey of heritage assets, where traditional approaches tend to fail.

关键词： image-based modeling Shape from Polarization Cultural heritage Specular reflection Normal estimation

来源：评论

学校读者我要写书评

暂无评论

A 1D-3D Hybrid Model of Patient-Specific Coronary Hemodynamics

引用

CARDIOVASCULAR ENGINEERING AND TECHNOLOGY 2022年第2期13卷 331-342页

作者： Gutierrez, Noelia Grande Sinno, Talid Diamond, Scott L. Univ Penn Dept Chem & Biomol Engn Philadelphia PA 19104 USA Univ Penn Dept Bioengn Philadelphia PA 19104 USA

Purpose Coronary flow is affected by evolving events such as atherosclerotic plaque formation, rupture, and thrombosis, resulting in myocardial ischemia and infarction. Highly resolved 3D hemodynamic data at the stenosis is essential to model shear-sensitive thrombotic events in coronary artery disease. Methods We developed a hybrid 1D-3D simulation framework to compute patient-specific coronary hemodynamics efficiently. A 1D model of the coronary flow is coupled to an image-based 3D model of the region of interest. This framework affords the advantages of reduced-order modeling, decreasing the global computational cost, without sacrificing the accuracy of the quantities of interest. Results We validated our 1D-3D model against full 3D coronary simulations in healthy and diseased conditions. Our results showed good agreement between the 3D and the 1D-3D models while reducing the computational cost by 40-fold compared to the 3D simulation. The 1D-3D model predicted left/right coronary flow distribution within 3% and provided an accurate estimation of fractional flow reserve and wall shear stress distribution at the stenosis comparable to the 3D simulation. Conclusion Savings in computational cost may be significant in situations with changing geometry, such as growing thrombosis. Also, this approach would allow quantifying the time-dependent effect of thrombotic growth and occlusion on the global coronary circulation.

关键词： Hemodynamics Coronary artery disease Coronary stenosis image-based modeling Reduced-order modeling

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：