首页 > 最新文献

Graphical Models最新文献

英文 中文
RFMNet: Robust Deep Functional Maps for unsupervised non-rigid shape correspondence RFMNet:无监督非刚性形状对应的鲁棒深度函数映射
IF 1.7 4区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING Pub Date : 2023-10-01 DOI: 10.1016/j.gmod.2023.101189
Ling Hu , Qinsong Li , Shengjun Liu , Dong-Ming Yan , Haojun Xu , Xinru Liu

In traditional deep functional maps for non-rigid shape correspondence, estimating a functional map including high-frequency information requires enough linearly independent features via the least square method, which is prone to be violated in practice, especially at an early stage of training, or costly post-processing, e.g. ZoomOut. In this paper, we propose a novel method called RFMNet (Robust Deep Functional Map Networks), which jointly considers training stability and more geometric shape features than previous works. We directly first produce a pointwise map by resorting to optimal transport and then convert it to an initial functional map. Such a mechanism mitigates the requirements for the descriptor and avoids the training instabilities resulting from the least square solver. Benefitting from the novel strategy, we successfully integrate a state-of-the-art geometric regularization for further optimizing the functional map, which substantially filters the initial functional map. We show our novel computing functional map module brings more stable training even under encoding the functional map with high-frequency information and faster convergence speed. Considering the pointwise and functional maps, an unsupervised loss is presented for penalizing the correspondence distortion of Delta functions between shapes. To catch discretization-resistant and orientation-aware shape features with our network, we utilize DiffusionNet as a feature extractor. Experimental results demonstrate our apparent superiority in correspondence quality and generalization across various shape discretizations and different datasets compared to the state-of-the-art learning methods.

在用于非刚性形状对应的传统深度函数图中,通过最小二乘法估计包括高频信息的函数图需要足够的线性独立特征,这在实践中很容易被违反,尤其是在训练的早期阶段,或者在昂贵的后处理(如ZoomOut)时。在本文中,我们提出了一种称为RFMNet(鲁棒深度函数映射网络)的新方法,该方法比以前的工作联合考虑了训练稳定性和更多的几何形状特征。我们首先通过采用最优传输直接生成逐点映射,然后将其转换为初始函数映射。这种机制减轻了对描述符的要求,并避免了由最小二乘解算器引起的训练不稳定性。得益于新策略,我们成功地集成了最先进的几何正则化来进一步优化函数图,该函数图对初始函数图进行了实质性滤波。我们展示了我们新颖的计算函数图模块,即使在对具有高频信息的函数图进行编码的情况下,也能带来更稳定的训练和更快的收敛速度。考虑到逐点映射和函数映射,提出了一种无监督损失来惩罚形状之间德尔塔函数的对应失真。为了用我们的网络捕捉抗离散化和方向感知的形状特征,我们使用DiffusionNet作为特征提取器。实验结果表明,与最先进的学习方法相比,我们在各种形状离散化和不同数据集的对应质量和泛化方面具有明显的优势。
{"title":"RFMNet: Robust Deep Functional Maps for unsupervised non-rigid shape correspondence","authors":"Ling Hu ,&nbsp;Qinsong Li ,&nbsp;Shengjun Liu ,&nbsp;Dong-Ming Yan ,&nbsp;Haojun Xu ,&nbsp;Xinru Liu","doi":"10.1016/j.gmod.2023.101189","DOIUrl":"https://doi.org/10.1016/j.gmod.2023.101189","url":null,"abstract":"<div><p>In traditional deep functional maps for non-rigid shape correspondence, estimating a functional map including high-frequency information requires enough linearly independent features via the least square method, which is prone to be violated in practice, especially at an early stage of training, or costly post-processing, e.g. ZoomOut. In this paper, we propose a novel method called RFMNet (<strong>R</strong>obust Deep <strong>F</strong>unctional <strong>M</strong>ap <strong>Net</strong>works), which jointly considers training stability and more geometric shape features than previous works. We directly first produce a pointwise map by resorting to optimal transport and then convert it to an initial functional map. Such a mechanism mitigates the requirements for the descriptor and avoids the training instabilities resulting from the least square solver. Benefitting from the novel strategy, we successfully integrate a state-of-the-art geometric regularization for further optimizing the functional map, which substantially filters the initial functional map. We show our novel computing functional map module brings more stable training even under encoding the functional map with high-frequency information and faster convergence speed. Considering the pointwise and functional maps, an unsupervised loss is presented for penalizing the correspondence distortion of Delta functions between shapes. To catch discretization-resistant and orientation-aware shape features with our network, we utilize DiffusionNet as a feature extractor. Experimental results demonstrate our apparent superiority in correspondence quality and generalization across various shape discretizations and different datasets compared to the state-of-the-art learning methods.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"129 ","pages":"Article 101189"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49889736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
MixNet: Mix different networks for learning 3D implicit representations MixNet:混合不同的网络来学习3D隐式表示
IF 1.7 4区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING Pub Date : 2023-10-01 DOI: 10.1016/j.gmod.2023.101190
Bowen Lyu , Li-Yong Shen , Chun-Ming Yuan

We introduce a neural network, MixNet, for learning implicit representations of 3D subtle models with large smooth areas and exact shape details in the form of interpolation of two different implicit functions. Our network takes a point cloud as input and uses conventional MLP networks and SIREN networks to predict different implicit fields. We use a learnable interpolation function to combine the implicit values of these two networks and achieve the respective advantages of them. The network is self-supervised with only reconstruction loss, leading to faithful 3D reconstructions with smooth planes, correct details, and plausible spatial partition without any ground-truth segmentation. We evaluate our method on ABC, the largest and most diverse CAD dataset, and some typical shapes to test in terms of geometric correctness and surface smoothness to demonstrate superiority over current alternatives suitable for shape reconstruction.

我们引入了一个神经网络MixNet,用于以两种不同隐式函数的插值形式学习具有大光滑区域和精确形状细节的3D精细模型的隐式表示。我们的网络以一个点云作为输入,使用传统的MLP网络和SIREN网络来预测不同的隐式域。我们使用一个可学习的插值函数将这两种网络的隐式值结合起来,实现它们各自的优势。该网络是自监督的,只有重建损失,导致忠实的三维重建,具有平滑的平面,正确的细节和合理的空间划分,没有任何地面真值分割。我们在ABC(最大和最多样化的CAD数据集)上评估了我们的方法,并在几何正确性和表面平滑度方面测试了一些典型的形状,以证明优于当前适合形状重建的替代方案。
{"title":"MixNet: Mix different networks for learning 3D implicit representations","authors":"Bowen Lyu ,&nbsp;Li-Yong Shen ,&nbsp;Chun-Ming Yuan","doi":"10.1016/j.gmod.2023.101190","DOIUrl":"https://doi.org/10.1016/j.gmod.2023.101190","url":null,"abstract":"<div><p>We introduce a neural network, MixNet, for learning implicit representations of 3D subtle models with large smooth areas and exact shape details in the form of interpolation of two different implicit functions. Our network takes a point cloud as input and uses conventional MLP networks and SIREN networks to predict different implicit fields. We use a learnable interpolation function to combine the implicit values of these two networks and achieve the respective advantages of them. The network is self-supervised with only reconstruction loss, leading to faithful 3D reconstructions with smooth planes, correct details, and plausible spatial partition without any ground-truth segmentation. We evaluate our method on ABC, the largest and most diverse CAD dataset, and some typical shapes to test in terms of geometric correctness and surface smoothness to demonstrate superiority over current alternatives suitable for shape reconstruction.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"129 ","pages":"Article 101190"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49890152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Fast progressive polygonal approximations for online strokes 快速渐进多边形近似在线笔画
IF 1.7 4区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING Pub Date : 2023-10-01 DOI: 10.1016/j.gmod.2023.101200
Mohammad Tanvir Parvez

This paper presents a fast and progressive polygonal approximation algorithm for online strokes. A stroke is defined as a sequence of points between a pen-down and a pen-up. The proposed method generates polygonal approximations progressively as the user inputs the stroke. The proposed algorithm is suitable for real time shape modeling and retrieval. The number of operations used in the proposed algorithm is bounded by O(n), where n is the number of points in a stroke. Detailed experimental results show that the proposed method is not only fast, but also accurate enough compared to other reported algorithms.

本文提出了一种快速渐进的在线笔画多边形逼近算法。笔画被定义为笔画和笔画之间的一系列点。该方法在用户输入笔画时逐步生成多边形近似值。该算法适用于实时形状建模和检索。所提出的算法中使用的操作数量以O(n)为限,其中n是笔画中的点的数量。详细的实验结果表明,与已有的算法相比,该方法不仅速度快,而且精度高。
{"title":"Fast progressive polygonal approximations for online strokes","authors":"Mohammad Tanvir Parvez","doi":"10.1016/j.gmod.2023.101200","DOIUrl":"10.1016/j.gmod.2023.101200","url":null,"abstract":"<div><p>This paper presents a fast and progressive polygonal approximation algorithm for online strokes. A stroke is defined as a sequence of points between a pen-down and a pen-up. The proposed method generates polygonal approximations progressively as the user inputs the stroke. The proposed algorithm is suitable for real time shape modeling and retrieval. The number of operations used in the proposed algorithm is bounded by O(<em>n</em>), where <em>n</em> is the number of points in a stroke. Detailed experimental results show that the proposed method is not only fast, but also accurate enough compared to other reported algorithms.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"129 ","pages":"Article 101200"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43203570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Unified shape and appearance reconstruction with joint camera parameter refinement 联合摄像机参数细化统一形状和外观重建
IF 1.7 4区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING Pub Date : 2023-10-01 DOI: 10.1016/j.gmod.2023.101193
Julian Kaltheuner, Patrick Stotko, Reinhard Klein

In this paper, we present an inverse rendering method for the simple reconstruction of shape and appearance of real-world objects from only roughly calibrated RGB images captured under collocated point light illumination. To this end, we gradually reconstruct the lower-frequency geometry information using automatically generated occupancy mask images based on a visual hull initialization of the mesh, to infer the object topology, and a smoothness-preconditioned optimization. By combining this geometry estimation with learning-based SVBRDF parameter inference as well as intrinsic and extrinsic camera parameter refinement in a joint and unified formulation, our novel method is able to reconstruct shape and an isotropic SVBRDF from fewer input images than previous methods. Unlike in other works, we also estimate normal maps as part of the SVBRDF to capture and represent higher-frequency geometric details in a compact way. Furthermore, by regularizing the appearance estimation with a GAN-based SVBRDF generator, we are able to meaningfully limit the solution space. In summary, this leads to a robust automatic reconstruction algorithm for shape and appearance. We evaluated our algorithm on synthetic as well as on real-world data and demonstrate that our method is able to reconstruct complex objects with high-fidelity reflection properties in a robust way, also in the presence of imperfect camera parameter data.

在本文中,我们提出了一种逆绘制方法,用于从在并置点光照明下捕获的粗略校准的RGB图像中简单重建现实世界物体的形状和外观。为此,我们基于网格的视觉船体初始化,使用自动生成的占用掩模图像逐步重建低频几何信息,推断物体拓扑,并进行平滑预处理优化。通过将这种几何估计与基于学习的SVBRDF参数推断以及在联合统一的公式中进行相机内外参数细化相结合,我们的新方法能够从比以前方法更少的输入图像中重建形状和各向同性SVBRDF。与其他作品不同,我们还估计法线贴图作为SVBRDF的一部分,以紧凑的方式捕获和表示高频几何细节。此外,通过使用基于gan的SVBRDF生成器对外观估计进行正则化,我们能够有效地限制解空间。综上所述,这导致了一种鲁棒的形状和外观自动重建算法。我们在合成数据和真实世界数据上评估了我们的算法,并证明我们的方法能够以稳健的方式重建具有高保真反射特性的复杂物体,即使存在不完美的相机参数数据。
{"title":"Unified shape and appearance reconstruction with joint camera parameter refinement","authors":"Julian Kaltheuner,&nbsp;Patrick Stotko,&nbsp;Reinhard Klein","doi":"10.1016/j.gmod.2023.101193","DOIUrl":"10.1016/j.gmod.2023.101193","url":null,"abstract":"<div><p>In this paper, we present an inverse rendering method for the simple reconstruction of shape and appearance of real-world objects from only roughly calibrated RGB images captured under collocated point light illumination. To this end, we gradually reconstruct the lower-frequency geometry information using automatically generated occupancy mask images based on a visual hull initialization of the mesh, to infer the object topology, and a smoothness-preconditioned optimization. By combining this geometry estimation with learning-based SVBRDF parameter inference as well as intrinsic and extrinsic camera parameter refinement in a joint and unified formulation, our novel method is able to reconstruct shape and an isotropic SVBRDF from fewer input images than previous methods. Unlike in other works, we also estimate normal maps as part of the SVBRDF to capture and represent higher-frequency geometric details in a compact way. Furthermore, by regularizing the appearance estimation with a GAN-based SVBRDF generator, we are able to meaningfully limit the solution space. In summary, this leads to a robust automatic reconstruction algorithm for shape and appearance. We evaluated our algorithm on synthetic as well as on real-world data and demonstrate that our method is able to reconstruct complex objects with high-fidelity reflection properties in a robust way, also in the presence of imperfect camera parameter data.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"129 ","pages":"Article 101193"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43340086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Unsupervised learning of style-aware facial animation from real acting performances 从真实表演中无监督地学习风格感知面部动画
IF 1.7 4区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING Pub Date : 2023-10-01 DOI: 10.1016/j.gmod.2023.101199
Wolfgang Paier , Anna Hilsmann , Peter Eisert

This paper presents a novel approach for text/speech-driven animation of a photo-realistic head model based on blend-shape geometry, dynamic textures, and neural rendering. Training a VAE for geometry and texture yields a parametric model for accurate capturing and realistic synthesis of facial expressions from a latent feature vector. Our animation method is based on a conditional CNN that transforms text or speech into a sequence of animation parameters. In contrast to previous approaches, our animation model learns disentangling/synthesizing different acting-styles in an unsupervised manner, requiring only phonetic labels that describe the content of training sequences. For realistic real-time rendering, we train a U-Net that refines rasterization-based renderings by computing improved pixel colors and a foreground matte. We compare our framework qualitatively/quantitatively against recent methods for head modeling as well as facial animation and evaluate the perceived rendering/animation quality in a user-study, which indicates large improvements compared to state-of-the-art approaches.

本文提出了一种基于混合形状几何、动态纹理和神经渲染的照片逼真头部模型的文本/语音驱动动画的新方法。训练用于几何和纹理的VAE产生用于从潜在特征向量精确捕捉和真实合成面部表情的参数模型。我们的动画方法基于条件CNN,它将文本或语音转换为一系列动画参数。与以前的方法相比,我们的动画模型以无监督的方式学习解开/合成不同的表演风格,只需要描述训练序列内容的语音标签。对于逼真的实时渲染,我们训练了一个U-Net,它通过计算改进的像素颜色和前景蒙版来改进基于光栅化的渲染。我们将我们的框架与最近的头部建模和面部动画方法进行了定性/定量比较,并在用户研究中评估了感知渲染/动画质量,这表明与最先进的方法相比有了很大的改进。
{"title":"Unsupervised learning of style-aware facial animation from real acting performances","authors":"Wolfgang Paier ,&nbsp;Anna Hilsmann ,&nbsp;Peter Eisert","doi":"10.1016/j.gmod.2023.101199","DOIUrl":"https://doi.org/10.1016/j.gmod.2023.101199","url":null,"abstract":"<div><p>This paper presents a novel approach for text/speech-driven animation of a photo-realistic head model based on blend-shape geometry, dynamic textures, and neural rendering. Training a VAE for geometry and texture yields a parametric model for accurate capturing and realistic synthesis of facial expressions from a latent feature vector. Our animation method is based on a conditional CNN that transforms text or speech into a sequence of animation parameters. In contrast to previous approaches, our animation model learns disentangling/synthesizing different acting-styles in an unsupervised manner, requiring only phonetic labels that describe the content of training sequences. For realistic real-time rendering, we train a U-Net that refines rasterization-based renderings by computing improved pixel colors and a foreground matte. We compare our framework qualitatively/quantitatively against recent methods for head modeling as well as facial animation and evaluate the perceived rendering/animation quality in a user-study, which indicates large improvements compared to state-of-the-art approaches.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"129 ","pages":"Article 101199"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49889738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Joint data and feature augmentation for self-supervised representation learning on point clouds 点云上自监督表示学习的联合数据和特征增强
IF 1.7 4区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING Pub Date : 2023-10-01 DOI: 10.1016/j.gmod.2023.101188
Zhuheng Lu , Yuewei Dai , Weiqing Li , Zhiyong Su

To deal with the exhausting annotations, self-supervised representation learning from unlabeled point clouds has drawn much attention, especially centered on augmentation-based contrastive methods. However, specific augmentations hardly produce sufficient transferability to high-level tasks on different datasets. Besides, augmentations on point clouds may also change underlying semantics. To address the issues, we propose a simple but efficient augmentation fusion contrastive learning framework to combine data augmentations in Euclidean space and feature augmentations in feature space. In particular, we propose a data augmentation method based on sampling and graph generation. Meanwhile, we design a data augmentation network to enable a correspondence of representations by maximizing consistency between augmented graph pairs. We further design a feature augmentation network that encourages the model to learn representations invariant to the perturbations using an encoder perturbation. We comprehensively conduct extensive object classification experiments and object part segmentation experiments to validate the transferability of the proposed framework. Experimental results demonstrate that the proposed framework is effective to learn the point cloud representation in a self-supervised manner, and yields state-of-the-art results in the community. The source code is publicly available at: https://github.com/VCG-NJUST/AFSRL.

为了解决标注耗尽的问题,从未标记的点云中进行自监督表示学习已经引起了人们的广泛关注,特别是基于增强的对比方法。然而,特定的增强很难产生足够的可移植性到不同数据集上的高级任务。此外,对点云的增强也可能改变底层语义。为了解决这些问题,我们提出了一种简单而有效的增强融合对比学习框架,将欧几里德空间中的数据增强和特征空间中的特征增强相结合。我们特别提出了一种基于采样和图生成的数据增强方法。同时,我们设计了一个数据增强网络,通过最大化增广图对之间的一致性来实现表示的对应。我们进一步设计了一个特征增强网络,鼓励模型学习对使用编码器扰动的扰动不变的表示。我们进行了广泛的目标分类实验和目标部分分割实验,以验证所提出框架的可移植性。实验结果表明,所提出的框架能够有效地以自监督的方式学习点云表示,并在社区中产生最先进的结果。源代码可以在:https://github.com/VCG-NJUST/AFSRL上公开获得。
{"title":"Joint data and feature augmentation for self-supervised representation learning on point clouds","authors":"Zhuheng Lu ,&nbsp;Yuewei Dai ,&nbsp;Weiqing Li ,&nbsp;Zhiyong Su","doi":"10.1016/j.gmod.2023.101188","DOIUrl":"https://doi.org/10.1016/j.gmod.2023.101188","url":null,"abstract":"<div><p>To deal with the exhausting annotations, self-supervised representation learning from unlabeled point clouds has drawn much attention, especially centered on augmentation-based contrastive methods. However, specific augmentations hardly produce sufficient transferability to high-level tasks on different datasets. Besides, augmentations on point clouds may also change underlying semantics. To address the issues, we propose a simple but efficient augmentation fusion contrastive learning framework to combine data augmentations in Euclidean space and feature augmentations in feature space. In particular, we propose a data augmentation method based on sampling and graph generation. Meanwhile, we design a data augmentation network to enable a correspondence of representations by maximizing consistency between augmented graph pairs. We further design a feature augmentation network that encourages the model to learn representations invariant to the perturbations using an encoder perturbation. We comprehensively conduct extensive object classification experiments and object part segmentation experiments to validate the transferability of the proposed framework. Experimental results demonstrate that the proposed framework is effective to learn the point cloud representation in a self-supervised manner, and yields state-of-the-art results in the community. The source code is publicly available at: <span>https://github.com/VCG-NJUST/AFSRL</span><svg><path></path></svg>.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"129 ","pages":"Article 101188"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49889741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Realistic simulation of fruit mildew diseases: Skin discoloration, fungus growth and volume shrinkage 水果霉菌病的真实模拟:皮肤变色、真菌生长和体积缩小
IF 1.7 4区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING Pub Date : 2023-10-01 DOI: 10.1016/j.gmod.2023.101194
Yixin Xu , Shiguang Liu

Time-varying effects simulation plays a critical role in computer graphics. Fruit diseases are typical time-varying phenomena. Due to the biological complexity, the existing methods fail to represent the biodiversity and biological law of symptoms. To this end, this paper proposes a biology-aware, physically-based framework that respects biological knowledge for realistic simulation of fruit mildew diseases. The simulated symptoms include skin discoloration, fungus growth, and volume shrinkage. Specifically, we take advantage of both the zero-order kinetic model and reaction–diffusion model to represent the complex fruit skin discoloration related to skin biological characteristics. To reproduce 3D mildew growth, we employ the Poisson-disk sampling technique and propose a template model instancing method. One can flexibly change hyphal template models to characterize the fungal biological diversity. To model the fruit’s biological structure, we fill the fruit mesh interior with particles in a biologically-based arrangement. Based on this structure, we propose a turgor pressure and a Lennard-Jones force-based adaptive mass–spring system to simulate the fruit shrinkage in a biological manner. Experiments verified that the proposed framework can effectively simulate mildew diseases, including gray mold, powdery mildew, and downy mildew. Our results are visually compelling and close to the ground truth. Both quantitative and qualitative experiments validated the proposed method.

时变效果仿真在计算机图形学中起着至关重要的作用。果实病害是典型的时变现象。由于生物的复杂性,现有的方法不能代表症状的生物多样性和生物学规律。为此,本文提出了一个尊重生物学知识的生物学意识,基于物理的框架,以实现水果霉病的真实模拟。模拟的症状包括皮肤变色、真菌生长和体积缩小。具体来说,我们利用零级动力学模型和反应-扩散模型来描述与皮肤生物学特性相关的复杂果皮变色。为了重现三维霉菌生长,我们采用了泊松盘采样技术,并提出了一种模板模型实例化方法。人们可以灵活地改变菌丝模板模型来表征真菌的生物多样性。为了模拟水果的生物结构,我们在水果网格内部填充了基于生物排列的颗粒。基于这种结构,我们提出了一个膨胀压力和一个基于Lennard-Jones力的自适应质量弹簧系统,以生物方式模拟果实收缩。实验验证了所提出的框架可以有效地模拟霉菌病,包括灰霉、白粉病和霜霉病。我们的结果在视觉上是令人信服的,接近地面的事实。定量和定性实验验证了该方法的有效性。
{"title":"Realistic simulation of fruit mildew diseases: Skin discoloration, fungus growth and volume shrinkage","authors":"Yixin Xu ,&nbsp;Shiguang Liu","doi":"10.1016/j.gmod.2023.101194","DOIUrl":"10.1016/j.gmod.2023.101194","url":null,"abstract":"<div><p>Time-varying effects simulation plays a critical role in computer graphics. Fruit diseases are typical time-varying phenomena. Due to the biological complexity, the existing methods fail to represent the biodiversity and biological law of symptoms. To this end, this paper proposes a biology-aware, physically-based framework that respects biological knowledge for realistic simulation of fruit mildew diseases. The simulated symptoms include skin discoloration, fungus growth, and volume shrinkage. Specifically, we take advantage of both the zero-order kinetic model and reaction–diffusion model to represent the complex fruit skin discoloration related to skin biological characteristics. To reproduce 3D mildew growth, we employ the Poisson-disk sampling technique and propose a template model instancing method. One can flexibly change hyphal template models to characterize the fungal biological diversity. To model the fruit’s biological structure, we fill the fruit mesh interior with particles in a biologically-based arrangement. Based on this structure, we propose a turgor pressure and a Lennard-Jones force-based adaptive mass–spring system to simulate the fruit shrinkage in a biological manner. Experiments verified that the proposed framework can effectively simulate mildew diseases, including gray mold, powdery mildew, and downy mildew. Our results are visually compelling and close to the ground truth. Both quantitative and qualitative experiments validated the proposed method.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"129 ","pages":"Article 101194"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41392551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Component-aware generative autoencoder for structure hybrid and shape completion 面向结构混合和形状补全的组件感知生成式自编码器
IF 1.7 4区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING Pub Date : 2023-10-01 DOI: 10.1016/j.gmod.2023.101185
Fan Zhang, Qiang Fu, Yang Liu, Xueming Li

Assembling components of man-made objects to create new structures or complete 3D shapes is a popular approach in 3D modeling techniques. Recently, leveraging deep neural networks for assembly-based 3D modeling has been widely studied. However, exploring new component combinations even across different categories is still challenging for most of the deep-learning-based 3D modeling methods. In this paper, we propose a novel generative autoencoder that tackles the component combinations for 3D modeling of man-made objects. We use the segmented input objects to create component volumes that have redundant components and random configurations. By using the input objects and the associated component volumes to train the autoencoder, we can obtain an object volume consisting of components with proper quality and structure as the network output. Such a generative autoencoder can be applied to either multiple object categories for structure hybrid or a single object category for shape completion. We conduct a series of evaluations and experimental results to demonstrate the usability and practicability of our method.

组装人造物体的组件以创建新的结构或完整的3D形状是3D建模技术中的一种流行方法。近年来,利用深度神经网络进行基于装配的三维建模得到了广泛的研究。然而,对于大多数基于深度学习的3D建模方法来说,探索跨不同类别的新组件组合仍然具有挑战性。在本文中,我们提出了一种新的生成式自编码器,用于解决人造物体三维建模的组件组合问题。我们使用分段输入对象来创建具有冗余组件和随机配置的组件卷。通过使用输入对象和相关联的分量体积对自编码器进行训练,我们可以得到一个由质量和结构合适的分量组成的对象体积作为网络输出。这种生成式自编码器既可以应用于多对象类别进行结构混合,也可以应用于单对象类别进行形状补全。我们进行了一系列的评估和实验结果,以证明我们的方法的可用性和实用性。
{"title":"Component-aware generative autoencoder for structure hybrid and shape completion","authors":"Fan Zhang,&nbsp;Qiang Fu,&nbsp;Yang Liu,&nbsp;Xueming Li","doi":"10.1016/j.gmod.2023.101185","DOIUrl":"https://doi.org/10.1016/j.gmod.2023.101185","url":null,"abstract":"<div><p>Assembling components of man-made objects to create new structures or complete 3D shapes is a popular approach in 3D modeling techniques. Recently, leveraging deep neural networks for assembly-based 3D modeling has been widely studied. However, exploring new component combinations even across different categories is still challenging for most of the deep-learning-based 3D modeling methods. In this paper, we propose a novel generative autoencoder that tackles the component combinations for 3D modeling of man-made objects. We use the segmented input objects to create component volumes that have redundant components and random configurations. By using the input objects and the associated component volumes to train the autoencoder, we can obtain an object volume consisting of components with proper quality and structure as the network output. Such a generative autoencoder can be applied to either multiple object categories for structure hybrid or a single object category for shape completion. We conduct a series of evaluations and experimental results to demonstrate the usability and practicability of our method.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"129 ","pages":"Article 101185"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49889740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Non-homogeneous denoising for virtual reality in real-time path tracing rendering 实时路径跟踪绘制中虚拟现实的非均匀去噪
IF 1.7 4区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING Pub Date : 2023-10-01 DOI: 10.1016/j.gmod.2023.101184
Victor Peres , Esteban Clua , Thiago Porcino , Anselmo Montenegro

Real time Path-tracing is becoming an important approach for the future of games, digital entertainment, and virtual reality applications that require realism and immersive environments. Among different possible optimizations, denoising Monte Carlo rendered images is necessary in low sampling densities. When dealing with Virtual Reality devices, other possibilities can also be considered, such as foveated rendering techniques. Hence, this work proposes a novel and promising rendering pipeline for denoising a real-time path-traced application in a dual-screen system such as head-mounted display (HMD) devices. Therefore, we leverage characteristics of the foveal vision by computing G-Buffers with the features of the scene and a buffer with the foveated distribution for both left and right screens. Later, we path trace the image within the coordinates buffer generating only a few initial rays per selected pixel, and reconstruct the noisy image output with a novel non-homogeneous denoiser that accounts for the pixel distribution. Our experiments showed that this proposed rendering pipeline could achieve a speedup factor up to 1.35 compared to one without our optimizations.

实时路径追踪正在成为未来游戏、数字娱乐和虚拟现实应用的重要方法,这些应用需要现实主义和沉浸式环境。在各种可能的优化中,在低采样密度下对蒙特卡罗渲染图像去噪是必要的。在处理虚拟现实设备时,还可以考虑其他可能性,例如注视点渲染技术。因此,这项工作提出了一种新颖而有前途的渲染管道,用于在双屏幕系统(如头戴式显示器(HMD)设备)中对实时路径跟踪应用进行去噪。因此,我们通过计算具有场景特征的G-Buffers和具有左右屏幕注视点分布的缓冲区来利用中央凹视觉的特征。随后,我们在坐标缓冲区内对图像进行路径跟踪,每个选定的像素只产生少量初始射线,并使用考虑像素分布的新型非均匀去噪器重建噪声图像输出。我们的实验表明,与没有优化的情况下相比,这个提议的渲染管道可以实现高达1.35的加速因子。
{"title":"Non-homogeneous denoising for virtual reality in real-time path tracing rendering","authors":"Victor Peres ,&nbsp;Esteban Clua ,&nbsp;Thiago Porcino ,&nbsp;Anselmo Montenegro","doi":"10.1016/j.gmod.2023.101184","DOIUrl":"10.1016/j.gmod.2023.101184","url":null,"abstract":"<div><p>Real time Path-tracing is becoming an important approach for the future of games, digital entertainment, and virtual reality applications that require realism and immersive environments. Among different possible optimizations, denoising Monte Carlo rendered images is necessary in low sampling densities. When dealing with Virtual Reality devices, other possibilities can also be considered, such as foveated rendering techniques. Hence, this work proposes a novel and promising rendering pipeline for denoising a real-time path-traced application in a dual-screen system such as head-mounted display (HMD) devices. Therefore, we leverage characteristics of the foveal vision by computing G-Buffers with the features of the scene and a buffer with the foveated distribution for both left and right screens. Later, we path trace the image within the coordinates buffer generating only a few initial rays per selected pixel, and reconstruct the noisy image output with a novel non-homogeneous denoiser that accounts for the pixel distribution. Our experiments showed that this proposed rendering pipeline could achieve a speedup factor up to 1.35 compared to one without our optimizations.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"129 ","pages":"Article 101184"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43863090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Obituary: Christoph M. Hoffmann 讣告:Christoph M. Hoffmann
IF 1.7 4区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING Pub Date : 2023-10-01 DOI: 10.1016/j.gmod.2023.101186
{"title":"Obituary: Christoph M. Hoffmann","authors":"","doi":"10.1016/j.gmod.2023.101186","DOIUrl":"10.1016/j.gmod.2023.101186","url":null,"abstract":"","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"129 ","pages":"Article 101186"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48312779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Graphical Models
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1