检索结果-内蒙古大学图书馆

14th International Workshop on Statistical Atlases and Computational Modelling of the Heart (STACOM)

作者： Muffoletto, Marica Xu, Hao Xu, Yiyang Williams, Steven E. Williams, Michelle C. Kunze, Karl P. Neji, Radhouene Niederer, Steven A. Rueckert, Daniel Young, Alistair A. Kings Coll London St Thomas Hosp Sch Biomed Engn & Imaging Sci 4th Floor Lambeth WingWestminster Bridge Rd London SW1 7EH England Univ Edinburgh Univ BHF Ctr Cardiovasc Sci 47 Little France Crescent Edinburgh EH16 4TJ Midlothian Scotland Siemens Healthcare Ltd MR Res Collaborat Frimley England Imperial Coll London Cardiac Electromech Res Grp CEMRG London England Tech Univ Munich Klinikum Rechts Isar Inst Artificial Intelligence & Informat Med Munich Germany

ISBN: (纸本)9783031524479;9783031524486

In cardiovascular magnetic resonance (CMR), typical acquisitions often involve a limited number of short and long axis slices. However, reconstructing the 3D chambers is crucial for accurately quantifying heart geometry and assessing cardiac function. neural implicit Representations (NIR) learn implicit functions for anatomical shapes from sparse measurements by leveraging a learned continuous shape prior, without the need for high-resolution ground truth data. In this study, we utilized coronary computed tomography (CCTA) images to simulate CMR sparse label maps of two types: standard (10mm spaced short axis and 2 long axis slices) and 3-slice (single short and 2 long axis slices). Whole heart NIR reconstructions were compared to a Label Completion U-Net (LC-U-Net) network trained on the dense segmentations. The findings indicate that the LC-U-Net is not robust when tested with fewer slices than those used during training. In contrast, the NIR consistently achieved Dice scores above 0.9 for the left ventricle, left ventricle myocardium, and right ventricle labels, irrespective of changes in the training or test set. Predictions from standard views achieved average Dice scores across all labels of 0.84 +/- 0.03 and 0.88 +/- 0.03, when training on 3-slice and standard data respectively. In conclusion, this study presents promising results for 3D shape reconstruction invariant to slice position and orientation without requiring full resolution training data, offering a robust and accurate method for cardiac chamber reconstruction in CMR.

关键词： CMR neural implicit functions 3D Reconstruction

来源：评论

学校读者我要写书评

暂无评论

Multi-NeuS: 3D Head Portraits From Single Image With neural implicit functions

引用

IEEE ACCESS 2023年 11卷 95681-95691页

作者： Burkov, Egor Rakhimov, Ruslan Safin, Aleksandr Burnaev, Evgeny Lempitsky, Victor Skolkovo Inst Sci & Technol Moscow 121205 Russia Artificial Intelligence Res Inst AIRI Moscow 121165 Russia

We present an approach for the reconstruction of textured 3D meshes of human heads from one or few views. Since such few-shot reconstruction is underconstrained, it requires prior knowledge which is hard to impose on traditional 3D reconstruction algorithms. In this work, we rely on the recently introduced 3D representation- neural implicit functions- which, being based on neural networks, allows to naturally learn priors about human heads from data, and is directly convertible to textured mesh. Namely, we extend NeuS, a state-of-the-art neural implicit function formulation, to represent multiple objects of a class (human heads in our case) simultaneously. The underlying neural net architecture is designed to learn the commonalities among these objects and to generalize to unseen ones. Our model is trained on just a hundred smartphone videos and does not require any scanned 3D data. Afterwards, the model can fit novel heads in the few-shot or one-shot modes with good results.

关键词： Three-dimensional displays Head Image reconstruction Metalearning Solid modeling Training neural engineering 3D portraits 3D reconstruction few-shot head reconstruction meta-learning neural implicit functions

来源：评论

学校读者我要写书评

暂无评论

Sparse Point Cloud Upsampling Based on neural implicit functions 1

引用

20th International Conference on Intelligent Computing (ICIC)

作者： Wang, Wenjun Kong, Xiangyu Wang, Daole Zhao, Xiuyang Univ Jinan Shandong Prov Key Lab Network Based Intelligent C Jinan Peoples R China Univ Jinan Sch Informat Sci & Engn Jinan Peoples R China

ISBN: (数字)9789819756001

ISBN: (纸本)9789819755998;9789819756001

In this paper, we propose a novel point cloud representation method based on neural implicit functions - spatial fields. This method utilizes neural implicit functions to transform three-dimensional coordinate points into local spatial fields, converting the original "discrete-discrete" point cloud representation into a "discrete-continuous" geometric representation, thereby to obtain continuous point cloud representations and richer geometric detail expression. In this method, each three-dimensional coordinate point in the original sparse point set is transformed into a local spatial field embedding multi-layer neighborhood information by means of implicit functions. Eventually, multiple such local spatial fields are aggregated into a continuous high-resolution spatial field to approximate the object surface as closely as possible. At last, arbitrary-scale sampling can be conducted in the high-resolution spatial field for point cloud densification needs at arbitrary resolutions in downstream applications such as 3D medical image reconstruction and autonomous driving. This paper provides an example to illustrate how to utilize the results of the proposed solution for 3D model reconstruction.

关键词： Sparse point cloud neural implicit functions upsampling Three-dimensional reconstruction

来源：评论

学校读者我要写书评

暂无评论

UNIF: United neural implicit functions for Clothed Human Reconstruction and Animation 1

引用

17th European Conference on Computer Vision (ECCV)

作者： Qian, Shenhan Xu, Jiale Liu, Ziwei Ma, Liqian Gao, Shenghua ZMO Inc Guangzhou Peoples R China ShanghaiTech Univ Shanghai Peoples R China Nanyang Technol Univ S Lab Singapore Singapore Shanghai Engn Res Ctr Intelligent Vision & Imagin Shanghai Peoples R China Shanghai Engn Res Ctr Energy Efficient & Custom A Shanghai Peoples R China

ISBN: (数字)9783031200625

ISBN: (纸本)9783031200618;9783031200625

We propose united implicit functions (UNIF), a part-based method for clothed human reconstruction and animation with raw scans and skeletons as the input. Previous part-based methods for human reconstruction rely on ground-truth part labels from SMPL and thus are limited to minimal-clothed humans. In contrast, our method learns to separate parts from body motions instead of part supervision, thus can be extended to clothed humans and other articulated objects. Our Partition-from-Motion is achieved by a bone-centered initialization, a bone limit loss, and a section normal loss that ensure stable part division even when the training poses are limited. We also present a minimal perimeter loss for SDF to suppress extra surfaces and part overlapping. Another core of our method is an adjacent part seaming algorithm that produces non-rigid deformations to maintain the connection between parts which significantly relieves the part-based artifacts. Under this algorithm, we further propose "Competing Parts", a method that defines blending weights by the relative position of a point to bones instead of the absolute position, avoiding the generalization problem of neural implicit functions with inverse LBS (linear blend skinning). We demonstrate the effectiveness of our method by clothed human body reconstruction and animation on the CAPE and the ClothSeq datasets. Our code is available at https://***/ShenhanQian/***.

关键词： Clothed human reconstruction neural implicit functions Shape representation Non-rigid deformation

来源：评论

学校读者我要写书评

暂无评论

neural implicit k-Space for Binning-Free Non-Cartesian Cardiac MR Imaging 28th

Neural Implicit k-Space for Binning-Free Non-Cartesian Cardi...

引用

28th International Conference on Information Processing in Medical Imaging (IPMI)

作者： Huang, Wenqi Li, Hongwei Bran Pan, Jiazhen Cruz, Gastao Rueckert, Daniel Hammernik, Kerstin Tech Univ Munich Munich Germany Univ Zurich Zurich Switzerland Univ Michigan Ann Arbor MI USA Imperial Coll London Dept Comp London England

ISBN: (纸本)9783031340475;9783031340482

In this work, we propose a novel image reconstruction framework that directly learns a neural implicit representation in k-space for ECG-triggered non-Cartesian Cardiac Magnetic Resonance Imaging (CMR). While existing methods bin acquired data from neighboring time points to reconstruct one phase of the cardiac motion, our framework allows for a continuous, binning-free, and subject-specific k-space representation. We assign a unique coordinate that consists of time, coil index, and frequency domain location to each sampled k-space point. We then learn the subject-specific mapping from these unique coordinates to k-space intensities using a multi-layer perceptron with frequency domain regularization. During inference, we obtain a complete k-space for Cartesian coordinates and an arbitrary temporal resolution. A simple inverse Fourier transform recovers the image, eliminating the need for density compensation and costly non-uniform Fourier transforms for non-Cartesian data. This novel imaging framework was tested on 42 radially sampled datasets from 6 subjects. The proposed method outperforms other techniques qualitatively and quantitatively using data from four and one heartbeat(s) and 30 cardiac phases. Our results for one heartbeat reconstruction of 50 cardiac phases show improved artifact removal and spatio-temporal resolution, leveraging the potential for real-time CMR. (Code available: https://***/wenqihuang/NIK MRI).

关键词： Image Reconstruction Non-Cartesian MRI Cardiac MRI neural implicit functions Deep Learning k-Space Interpolation

来源：评论

学校读者我要写书评

暂无评论

Layered-Garment Net: Generating Multiple implicit Garment Layers from a Single Image 16th

Layered-Garment Net: Generating Multiple Implicit Garment La...

引用

16th Asian Conference on Computer Vision (ACCV)

作者： Aggarwal, Alakh Wang, Jikai Hogue, Steven Ni, Saifeng Budagavi, Madhukar Guo, Xiaohu Univ Texas Dallas Richardson TX 75083 USA Samsung Res Amer Plano TX USA

ISBN: (纸本)9783031263187;9783031263194

Recent research works have focused on generating human models and garments from their 2D images. However, state-of-the-art researches focus either on only a single layer of the garment on a human model or on generating multiple garment layers without any guarantee of the intersection-free geometric relationship between them. In reality, people wear multiple layers of garments in their daily life, where an inner layer of garment could be partially covered by an outer one. In this paper, we try to address this multi-layer modeling problem and propose the Layered-Garment Net (LGN) that is capable of generating intersection-free multiple layers of garments defined by implicit function fields over the body surface, given the person's near front-view image. With a special design of garment indication fields (GIF), we can enforce an implicit covering relationship between the signed distance fields (SDF) of different layers to avoid self-intersections among different garment surfaces and the human body. Experiments demonstrate the strength of our proposed LGN framework in generating multi-layer garments as compared to state-of-the-art methods. To the best of our knowledge, LGN is the first research work to generate intersection-free multiple layers of garments on the human body from a single image.

关键词： Image-based reconstruction Multi-layered garments neural implicit functions Intersection-free

来源：评论

学校读者我要写书评

暂无评论

ARAH: Animatable Volume Rendering of Articulated Human SDFs 1

引用

17th European Conference on Computer Vision (ECCV)

作者： Wang, Shaofei Schwarz, Katja Geiger, Andreas Tang, Siyu Swiss Fed Inst Technol Zurich Switzerland Max Planck Inst Intelligent Syst Tubingen Germany Univ Tubingen Tubingen Germany

ISBN: (数字)9783031198243

ISBN: (纸本)9783031198236;9783031198243

Combining human body models with differentiable rendering has recently enabled animatable avatars of clothed humans from sparse sets of multi-view RGB videos. While state-of-the-art approaches achieve a realistic appearance with neural radiance fields (NeRF), the inferred geometry often lacks detail due to missing geometric constraints. Further, animating avatars in out-of-distribution poses is not yet possible because the mapping from observation space to canonical space does not generalize faithfully to unseen poses. In this work, we address these shortcomings and propose a model to create animatable clothed human avatars with detailed geometry that generalize well to out-of-distribution poses. To achieve detailed geometry, we combine an articulated implicit surface representation with volume rendering. For generalization, we propose a novel joint root-finding algorithm for simultaneous ray-surface intersection search and correspondence search. Our algorithm enables efficient point sampling and accurate point canonicalization while generalizing well to unseen poses. We demonstrate that our proposed pipeline can generate clothed avatars with high-quality pose-dependent geometry and appearance from a sparse set of multi-view RGB videos. Our method achieves state-of-the-art performance on geometry and appearance reconstruction while creating animatable avatars that generalize well to out-of-distribution poses beyond the small number of training poses.

关键词： 3D computer vision Clothed human modeling Cloth modeling neural rendering neural implicit functions

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：