Representing shapes as level sets of neural networks has been recently proved to be useful for different shape analysis and reconstruction tasks. So far, such representations were computed using either: (i) pre-computed implicit shape representations; or (ii) loss functions explicitly defined over the neural level sets.In this paper we offer a new paradigm for computing high fidelity implicit neural representations directly from raw data (i.e., point clouds, with or without normal information). We observe that a rather simple loss function, encouraging the neural network to vanish on the input point cloud and to have a unit norm gradient, possesses an implicit geometric regularization property that favors smooth and natural zero level set surfaces, avoiding bad zero-loss solutions.We provide a theoretical analysis of this property for the linear case, and show that, in practice, our method leads to state of the art implicit neural representations with higher level-of-details and fidelity compared to previous methods.
translated by 谷歌翻译
Figure 1: We introduce SAL: Sign Agnostic Learning for learning shapes directly from raw data, such as triangle soups (left in each gray pair; back-faces are in red). Right in each gray pair -the surface reconstruction by SAL of test raw scans; in gold -SAL latent space interpolation between adjacent gray shapes. Raw scans are from the D-Faust dataset [8].
translated by 谷歌翻译
我们引入了一个神经隐式框架,该框架利用神经网络的可区分特性和点采样表面的离散几何形状,以将它们作为神经隐含函数的级别集近似。为了训练神经隐式函数,我们提出了近似签名距离函数的损失功能,并允许具有高阶导数的术语,例如曲率的主要方向之间的对齐方式,以了解更多几何细节。在训练过程中,我们考虑了基于点采样表面的曲率的不均匀采样策略,以优先考虑点更多的几何细节。与以前的方法相比,这种抽样意味着在保持几何准确性的同时更快地学习。我们还介绍了神经表面(例如正常矢量和曲率)的分析差异几何公式。
translated by 谷歌翻译
将3D坐标映射到签名距离函数(SDF)或占用值的神经网络具有启用对象形状的高保真隐式表示。本文开发了一种新的形状模型,允许通过优化连续符号定向距离功能(SDDF)来合成新颖距离视图。与Deep SDF模型类似,我们的SDDF配方可以代表整个类别的形状并从部分输入数据中跨越形状填写或插入。与SDF不同,该SDF在任何方向上测量到最近表面的距离,SDDF测量给定方向的距离。这允许训练没有3D形状监控的SDDF模型,仅使用距离测量,从深度相机或激光雷达传感器易获得。我们的模型还通过直接在任意位置和观察方向上直接预测距离,去除像表面提取或渲染的后处理步骤。与深色视角综合技术不同,例如培训高容量黑盒型号的神经辐射字段,我们的模型通过构造SDDF值沿着观察方向线性降低的性质。这种结构约束不仅导致维度降低,而且还提供了关于SDDF预测的准确性的分析信心,无论到物体表面的距离如何。
translated by 谷歌翻译
In this work we address the challenging problem of multiview 3D surface reconstruction. We introduce a neural network architecture that simultaneously learns the unknown geometry, camera parameters, and a neural renderer that approximates the light reflected from the surface towards the camera. The geometry is represented as a zero level-set of a neural network, while the neural renderer, derived from the rendering equation, is capable of (implicitly) modeling a wide set of lighting conditions and materials. We trained our network on real world 2D images of objects with different material properties, lighting conditions, and noisy camera initializations from the DTU MVS dataset. We found our model to produce state of the art 3D surface reconstructions with high fidelity, resolution and detail.
translated by 谷歌翻译
Figure 1: DeepSDF represents signed distance functions (SDFs) of shapes via latent code-conditioned feed-forward decoder networks. Above images are raycast renderings of DeepSDF interpolating between two shapes in the learned shape latent space. Best viewed digitally.
translated by 谷歌翻译
最近对隐含形状表示的兴趣日益增长。与明确的陈述相反,他们没有解决局限性,他们很容易处理各种各样的表面拓扑。为了了解这些隐式表示,电流方法依赖于一定程度的形状监督(例如,内部/外部信息或距离形状知识),或者至少需要密集点云(以近似距离 - 到 - 到 - 形状)。相比之下,我们介绍{\方法},一种用于学习形状表示的自我监督方法,从可能极其稀疏的点云。就像在水牛的针问题一样,我们在点云上“掉落”(样本)针头,认为,静统计地靠近表面,针端点位于表面的相对侧。不需要形状知识,点云可以高稀疏,例如,作为车辆获取的Lidar点云。以前的自我监督形状表示方法未能在这种数据上产生良好的结果。我们获得定量结果与现有的形状重建数据集上现有的监督方法标准,并在Kitti等硬自动驾驶数据集中显示有前途的定性结果。
translated by 谷歌翻译
从嘈杂,不均匀和无知点云中的表面重建是计算机视觉和图形中的一个令人迷人但具有挑战性的问题。随着3D扫描技术的创新,强烈希望直接转换原始扫描数据,通常具有严重噪声,进入歧管三角网格。现有的基于学习的方法旨在学习零级曲面对底层形状进行的隐式功能。然而,大多数人都无法获得嘈杂和稀疏点云的理想结果,限制在实践中。在本文中,我们介绍了神经IML,一种新的方法,它直接从未引起的原始点云学习抗噪声符号距离功能(SDF)。通过最大限度地减少由隐式移动最小二乘函数获得的损耗,我们的方法通过最小化了自我监督的方式,从原始点云中从原始点云中的底层SDF,而不是明确地学习前提。 (IML)和我们的神经网络另一个,我们的预测器的梯度定义了便于计算IML的切线束。我们证明,当几个SDFS重合时,我们的神经网络可以预测符号隐式功能,其零电平集用作底层表面的良好近似。我们对各种基准进行广泛的实验,包括合成扫描和现实世界扫描,以表现出从各种投入重建忠实形状的能力,特别是对于具有噪音或间隙的点云。
translated by 谷歌翻译
由于其成功在从稀疏的输入图像集合中合成了场景的新颖视图,最近越来越受欢迎。到目前为止,通过通用密度函数建模了神经体积渲染技术的几何形状。此外,使用通向嘈杂的任意水平函数的任意水平集合来提取几何形状本身,通常是低保真重建。本文的目标是改善神经体积渲染中的几何形象和重建。我们通过将体积密度建模为几何形状来实现这一点。这与以前的工作与体积密度的函数建模几何。更详细地,我们将音量密度函数定义为Laplace的累积分发功能(CDF)应用于符号距离功能(SDF)表示。这种简单的密度表示有三个好处:(i)它为神经体积渲染过程中学到的几何形状提供了有用的电感偏差; (ii)它促进了缺陷近似误差的束缚,导致观看光线的准确采样。精确的采样对于提供几何和光线的精确耦合非常重要; (iii)允许高效无监督的脱位形状和外观在体积渲染中。将此新密度表示应用于具有挑战性的场景多视图数据集生产了高质量的几何重建,表现优于相关的基线。此外,由于两者的解剖学,场景之间的切换形状和外观是可能的。
translated by 谷歌翻译
Neural network-based approaches for solving partial differential equations (PDEs) have recently received special attention. However, the large majority of neural PDE solvers only apply to rectilinear domains, and do not systematically address the imposition of Dirichlet/Neumann boundary conditions over irregular domain boundaries. In this paper, we present a framework to neurally solve partial differential equations over domains with irregularly shaped (non-rectilinear) geometric boundaries. Our network takes in the shape of the domain as an input (represented using an unstructured point cloud, or any other parametric representation such as Non-Uniform Rational B-Splines) and is able to generalize to novel (unseen) irregular domains; the key technical ingredient to realizing this model is a novel approach for identifying the interior and exterior of the computational grid in a differentiable manner. We also perform a careful error analysis which reveals theoretical insights into several sources of error incurred in the model-building process. Finally, we showcase a wide variety of applications, along with favorable comparisons with ground truth solutions.
translated by 谷歌翻译
最近的工作建模3D开放表面培训深度神经网络以近似无符号距离字段(UDF)并隐含地代表形状。要将此表示转换为显式网格,它们要么使用计算上昂贵的方法来对表面的致密点云采样啮合,或者通过将其膨胀到符号距离字段(SDF)中来扭曲表面。相比之下,我们建议直接将深度UDFS直接以延伸行进立方体的开放表面,通过本地检测表面交叉。我们的方法是幅度的序列,比啮合致密点云,比膨胀开口表面更准确。此外,我们使我们的表面提取可微分,并显示它可以帮助稀疏监控信号。
translated by 谷歌翻译
Figure 1. Given input as either a 2D image or a 3D point cloud (a), we automatically generate a corresponding 3D mesh (b) and its atlas parameterization (c). We can use the recovered mesh and atlas to apply texture to the output shape (d) as well as 3D print the results (e).
translated by 谷歌翻译
近年来,由于其表达力和灵活性,神经隐式表示在3D重建中获得了普及。然而,神经隐式表示的隐式性质导致缓慢的推理时间并且需要仔细初始化。在本文中,我们重新审视经典且无处不在的点云表示,并使用泊松表面重建(PSR)的可分辨率配方引入可分化的点对网格层,其允许给予定向的GPU加速的指示灯的快速解决方案点云。可微分的PSR层允许我们通过隐式指示器字段有效地和分散地桥接与3D网格的显式3D点表示,从而实现诸如倒角距离的表面重建度量的端到端优化。因此,点和网格之间的这种二元性允许我们以面向点云表示形状,这是显式,轻量级和富有表现力的。与神经内隐式表示相比,我们的形状 - 点(SAP)模型更具可解释,轻量级,并通过一个级别加速推理时间。与其他显式表示相比,如点,补丁和网格,SA​​P产生拓扑无关的水密歧管表面。我们展示了SAP对无知点云和基于学习的重建的表面重建任务的有效性。
translated by 谷歌翻译
基于坐标的神经网络参数化隐式表面已成为几何形状的有效表示。它们有效地充当参数水平集,其零级集合定义了感兴趣的表面。我们提出了一个框架,该框架允许将定义的三角形网格定义的变形操作应用于此类隐式表面。这些操作中的几个可以看作是能量最小化的问题,这些问题会诱导显式表面上的瞬时流场。我们的方法使用流场通过扩展级别集的经典理论来变形参数隐式表面。我们还通过形式化与级别集理论的联系,来得出有关可区分表面提取和渲染的现有方法的合并视图。我们表明,这些方法从理论中偏离,我们的方法对诸如表面平滑,均值流动,反向渲染和用户定义的编辑等应用进行了改进。
translated by 谷歌翻译
在两个非辅助变形形状之间建立对应关系是视觉计算中最根本的问题之一。当对现实世界中的挑战(例如噪声,异常值,自我结合等)挑战时,现有方法通常会显示出弱的弹性。另一方面,自动描述器在学习几何学上有意义的潜在嵌入方面表现出强大的表现力。但是,它们在\ emph {形状分析}中的使用受到限制。在本文中,我们介绍了一种基于自动码头框架的方法,该方法在固定模板上学习了一个连续形状的变形字段。通过监督点在表面上的变形场,并通过小说\ emph {签名距离正则化}(SDR)正规化点偏面的正规化,我们学习了模板和Shape \ Emph {卷}之间的对齐。经过干净的水密网眼培训,\ emph {没有}任何数据启发,我们证明了在受损的数据和现实世界扫描上表现出令人信服的性能。
translated by 谷歌翻译
Implicitly defined, continuous, differentiable signal representations parameterized by neural networks have emerged as a powerful paradigm, offering many possible benefits over conventional representations. However, current network architectures for such implicit neural representations are incapable of modeling signals with fine detail, and fail to represent a signal's spatial and temporal derivatives, despite the fact that these are essential to many physical signals defined implicitly as the solution to partial differential equations. We propose to leverage periodic activation functions for implicit neural representations and demonstrate that these networks, dubbed sinusoidal representation networks or SIRENs, are ideally suited for representing complex natural signals and their derivatives. We analyze SIREN activation statistics to propose a principled initialization scheme and demonstrate the representation of images, wavefields, video, sound, and their derivatives. Further, we show how SIRENs can be leveraged to solve challenging boundary value problems, such as particular Eikonal equations (yielding signed distance functions), the Poisson equation, and the Helmholtz and wave equations. Lastly, we combine SIRENs with hypernetworks to learn priors over the space of SIREN functions. Please see the project website for a video overview of the proposed method and all applications.
translated by 谷歌翻译
形状空间学习的任务涉及使用良好的概括性属性映射到从潜在表示空间的列车组。通常,真实世界的形状系列具有对称性,可以定义为不改变形状本质的转换。在形状空间学习中纳入对称性的自然方式是要求将其映射到形状空间(编码器)和从形状空间(解码器)映射到相关的对称。在本文中,我们通过引入两个贡献,提出了一种在编码器和解码器中融入设备和解码器的框架:(i)适应建设通用,高效和最大富有表现力的Autorencoders的最近帧平均(FA)框架; (ii)构建自动化器等于分段欧几里德运动的分段应用于形状的不同部分。据我们所知,这是第一个完全分段的欧几里德的欧洲等自动化器建设。培训我们的框架很简单:它使用标准的重建损失,不需要引入新的损失。我们的体系结构由标准(骨干网)架构构成,具有适当的帧平均,使其成为等效。使用隐式的神经表示,在两个刚性形状数据集上测试我们的框架,并使用基于网格的神经网络的铰接形状数据集显示出技术的概括,以通过大边缘改善相关基线。特别地,我们的方法表明了概括铰接姿势的概括性的显着改善。
translated by 谷歌翻译
神经隐式功能最近显示了来自多个视图的表面重建的有希望的结果。但是,当重建无限或复杂的场景时,当前的方法仍然遭受过度复杂性和稳健性不佳。在本文中,我们介绍了RegSDF,这表明适当的点云监督和几何正规化足以产生高质量和健壮的重建结果。具体而言,RegSDF将额外的定向点云作为输入,并优化了可区分渲染框架内的签名距离字段和表面灯场。我们还介绍了这两个关键的正规化。第一个是在给定嘈杂和不完整输入的整个距离字段中平稳扩散签名距离值的Hessian正则化。第二个是最小的表面正则化,可紧凑并推断缺失的几何形状。大量实验是在DTU,BlendenDMV以及储罐和寺庙数据集上进行的。与最近的神经表面重建方法相比,RegSDF即使对于具有复杂拓扑和非结构化摄像头轨迹的开放场景,RegSDF也能够重建表面。
translated by 谷歌翻译
We propose a differentiable sphere tracing algorithm to bridge the gap between inverse graphics methods and the recently proposed deep learning based implicit signed distance function. Due to the nature of the implicit function, the rendering process requires tremendous function queries, which is particularly problematic when the function is represented as a neural network. We optimize both the forward and backward passes of our rendering layer to make it run efficiently with affordable memory consumption on a commodity graphics card. Our rendering method is fully differentiable such that losses can be directly computed on the rendered 2D observations, and the gradients can be propagated backwards to optimize the 3D geometry. We show that our rendering method can effectively reconstruct accurate 3D shapes from various inputs, such as sparse depth and multi-view images, through inverse optimization. With the geometry based reasoning, our 3D shape prediction methods show excellent generalization capability and robustness against various noises. * Work done while Shaohui Liu was an academic guest at ETH Zurich.
translated by 谷歌翻译