allows us to train our model in the variational inference framework. Empirically, we demonstrate that PointFlow achieves state-of-the-art performance in point cloud generation. We additionally show that our model can faithfully reconstruct point clouds and learn useful representations in an unsupervised manner. The code is available at https: //github.com/stevenygd/PointFlow.
translated by 谷歌翻译
We present a probabilistic model for point cloud generation, which is fundamental for various 3D vision tasks such as shape completion, upsampling, synthesis and data augmentation. Inspired by the diffusion process in nonequilibrium thermodynamics, we view points in point clouds as particles in a thermodynamic system in contact with a heat bath, which diffuse from the original distribution to a noise distribution. Point cloud generation thus amounts to learning the reverse diffusion process that transforms the noise distribution to the distribution of a desired shape. Specifically, we propose to model the reverse diffusion process for point clouds as a Markov chain conditioned on certain shape latent. We derive the variational bound in closed form for training and provide implementations of the model. Experimental results demonstrate that our model achieves competitive performance in point cloud generation and auto-encoding. The code is available at https://github.com/luost26/diffusionpoint-cloud.
translated by 谷歌翻译
最近归一化流量(NFS)在建模3D点云上已经证明了最先进的性能,同时允许在推理时间以任意分辨率进行采样。然而,这些基于流的模型仍然需要长期训练时间和大型模型来代表复杂的几何形状。这项工作通过将NFS的混合物应用于点云来增强它们的代表性。我们展示在更普遍的框架中,每个组件都学会专门以完全无监督的方式专门化对象的特定子区域。通过将每个混合组件与相对小的NF实例化,我们通过更好的细节生成点云,而与基于单流量的模型相比,使用较少的参数,并且大大减少推理运行时。我们进一步证明通过添加数据增强,各个混合组件可以学习以语义有意义的方式专注。基于ShapEnet​​ DataSet评估NFS对生成,自动编码和单视重建的混合物。
translated by 谷歌翻译
Three-dimensional geometric data offer an excellent domain for studying representation learning and generative modeling. In this paper, we look at geometric data represented as point clouds. We introduce a deep AutoEncoder (AE) network with state-of-the-art reconstruction quality and generalization ability. The learned representations outperform existing methods on 3D recognition tasks and enable shape editing via simple algebraic manipulations, such as semantic part editing, shape analogies and shape interpolation, as well as shape completion. We perform a thorough study of different generative models including GANs operating on the raw point clouds, significantly improved GANs trained in the fixed latent space of our AEs, and Gaussian Mixture Models (GMMs). To quantitatively evaluate generative models we introduce measures of sample fidelity and diversity based on matchings between sets of point clouds. Interestingly, our evaluation of generalization, fidelity and diversity reveals that GMMs trained in the latent space of our AEs yield the best results overall.
translated by 谷歌翻译
Generative models, as an important family of statistical modeling, target learning the observed data distribution via generating new instances. Along with the rise of neural networks, deep generative models, such as variational autoencoders (VAEs) and generative adversarial network (GANs), have made tremendous progress in 2D image synthesis. Recently, researchers switch their attentions from the 2D space to the 3D space considering that 3D data better aligns with our physical world and hence enjoys great potential in practice. However, unlike a 2D image, which owns an efficient representation (i.e., pixel grid) by nature, representing 3D data could face far more challenges. Concretely, we would expect an ideal 3D representation to be capable enough to model shapes and appearances in details, and to be highly efficient so as to model high-resolution data with fast speed and low memory cost. However, existing 3D representations, such as point clouds, meshes, and recent neural fields, usually fail to meet the above requirements simultaneously. In this survey, we make a thorough review of the development of 3D generation, including 3D shape generation and 3D-aware image synthesis, from the perspectives of both algorithms and more importantly representations. We hope that our discussion could help the community track the evolution of this field and further spark some innovative ideas to advance this challenging task.
translated by 谷歌翻译
Point Cloud升级旨在从给定的稀疏中产生密集的点云,这是一项具有挑战性的任务,这是由于点集的不规则和无序的性质。为了解决这个问题,我们提出了一种新型的基于深度学习的模型,称为PU-Flow,该模型结合了正常的流量和权重预测技术,以产生均匀分布在基础表面上的致密点。具体而言,我们利用标准化流的可逆特征来转换欧几里得和潜在空间之间的点,并将UPSMPLING过程作为潜在空间中相邻点的集合,从本地几何环境中自适应地学习。广泛的实验表明,我们的方法具有竞争力,并且在大多数测试用例中,它在重建质量,近距到表面的准确性和计算效率方面的表现优于最先进的方法。源代码将在https://github.com/unknownue/pu-flow上公开获得。
translated by 谷歌翻译
标准化流(NFS)是灵活的显式生成模型,已被证明可以准确地对复杂的现实世界数据分布进行建模。但是,它们的可逆性限制对存在于嵌入较高维空间中的较低维歧管上的数据分布施加局限性。实际上,这种缺点通常通过在影响生成样品质量的数据中添加噪声来绕过。与先前的工作相反,我们通过从原始数据分布中生成样品来解决此问题,并有有关扰动分布和噪声模型的全部知识。为此,我们确定对受扰动数据训练的NFS隐式表示最大可能性区域中的歧管。然后,我们提出了一个优化目标,该目标从扰动分布中恢复了歧管上最有可能的点。最后,我们专注于我们利用NFS的明确性质的3D点云,即从对数似然梯度中提取的表面正态和对数类样本本身,将Poisson表面重建应用于精炼生成的点集。
translated by 谷歌翻译
We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder, called IM-NET, for shape generation, aimed at improving the visual quality of the generated shapes. An implicit field assigns a value to each point in 3D space, so that a shape can be extracted as an iso-surface. IM-NET is trained to perform this assignment by means of a binary classifier. Specifically, it takes a point coordinate, along with a feature vector encoding a shape, and outputs a value which indicates whether the point is outside the shape or not. By replacing conventional decoders by our implicit decoder for representation learning (via IM-AE) and shape generation (via IM-GAN), we demonstrate superior results for tasks such as generative shape modeling, interpolation, and single-view 3D reconstruction, particularly in terms of visual quality. Code and supplementary material are available at https://github.com/czq142857/implicit-decoder.
translated by 谷歌翻译
Diffusion models have shown great promise for image generation, beating GANs in terms of generation diversity, with comparable image quality. However, their application to 3D shapes has been limited to point or voxel representations that can in practice not accurately represent a 3D surface. We propose a diffusion model for neural implicit representations of 3D shapes that operates in the latent space of an auto-decoder. This allows us to generate diverse and high quality 3D surfaces. We additionally show that we can condition our model on images or text to enable image-to-3D generation and text-to-3D generation using CLIP embeddings. Furthermore, adding noise to the latent codes of existing shapes allows us to explore shape variations.
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
In recent years, substantial progress has been achieved in learning-based reconstruction of 3D objects. At the same time, generative models were proposed that can generate highly realistic images. However, despite this success in these closely related tasks, texture reconstruction of 3D objects has received little attention from the research community and state-of-the-art methods are either limited to comparably low resolution or constrained experimental setups. A major reason for these limitations is that common representations of texture are inefficient or hard to interface for modern deep learning techniques. In this paper, we propose Texture Fields, a novel texture representation which is based on regressing a continuous 3D function parameterized with a neural network. Our approach circumvents limiting factors like shape discretization and parameterization, as the proposed texture representation is independent of the shape representation of the 3D object. We show that Texture Fields are able to represent high frequency texture and naturally blend with modern deep learning techniques. Experimentally, we find that Texture Fields compare favorably to state-of-the-art methods for conditional texture reconstruction of 3D objects and enable learning of probabilistic generative models for texturing unseen 3D models. We believe that Texture Fields will become an important building block for the next generation of generative 3D models.
translated by 谷歌翻译
点云降级旨在从噪音和异常值损坏的原始观察结果中恢复清洁点云,同时保留细粒细节。我们提出了一种新型的基于深度学习的DeNoising模型,该模型结合了正常的流量和噪声解散技术,以实现高降解精度。与提取点云特征以进行点校正的现有作品不同,我们从分布学习和特征分离的角度制定了denoising过程。通过将嘈杂的点云视为清洁点和噪声的联合分布,可以从将噪声对应物从潜在点表示中解​​散出来,而欧几里得和潜在空间之间的映射是通过标准化流量来建模的。我们评估了具有各种噪声设置的合成3D模型和现实世界数据集的方法。定性和定量结果表明,我们的方法表现优于先前的最先进的基于深度学习的方法。
translated by 谷歌翻译
变异推理(VI)的核心原理是将计算复杂后概率密度计算的统计推断问题转换为可拖动的优化问题。该属性使VI比几种基于采样的技术更快。但是,传统的VI算法无法扩展到大型数据集,并且无法轻易推断出越野数据点,而无需重新运行优化过程。该领域的最新发展,例如随机,黑框和摊销VI,已帮助解决了这些问题。如今,生成的建模任务广泛利用摊销VI来实现其效率和可扩展性,因为它利用参数化函数来学习近似的后验密度参数。在本文中,我们回顾了各种VI技术的数学基础,以构成理解摊销VI的基础。此外,我们还概述了最近解决摊销VI问题的趋势,例如摊销差距,泛化问题,不一致的表示学习和后验崩溃。最后,我们分析了改善VI优化的替代差异度量。
translated by 谷歌翻译
近似复杂的概率密度是现代统计中的核心问题。在本文中,我们介绍了变分推理(VI)的概念,这是一种机器学习中的流行方法,该方法使用优化技术来估计复杂的概率密度。此属性允许VI汇聚速度比经典方法更快,例如Markov Chain Monte Carlo采样。概念上,VI通过选择一个概率密度函数,然后找到最接近实际概率密度的家庭 - 通常使用Kullback-Leibler(KL)发散作为优化度量。我们介绍了缩窄的证据,以促进近似的概率密度,我们审查了平均场变分推理背后的想法。最后,我们讨论VI对变分式自动编码器(VAE)和VAE-生成的对抗网络(VAE-GAN)的应用。用本文,我们的目标是解释VI的概念,并通过这种方法协助协助。
translated by 谷歌翻译
我们为3D形状生成(称为SDF-Stylegan)提供了一种基于stylegan2的深度学习方法,目的是降低生成形状和形状集合之间的视觉和几何差异。我们将stylegan2扩展到3D世代,并利用隐式签名的距离函数(SDF)作为3D形状表示,并引入了两个新颖的全球和局部形状鉴别器,它们区分了真实和假的SDF值和梯度,以显着提高形状的几何形状和视觉质量。我们进一步补充了基于阴影图像的FR \'Echet Inception距离(FID)分数的3D生成模型的评估指标,以更好地评估生成形状的视觉质量和形状分布。对形状生成的实验证明了SDF-Stylegan比最先进的表现出色。我们进一步证明了基于GAN倒置的各种任务中SDF-Stylegan的功效,包括形状重建,部分点云的形状完成,基于单图像的形状形状生成以及形状样式编辑。广泛的消融研究证明了我们框架设计的功效。我们的代码和训练有素的模型可在https://github.com/zhengxinyang/sdf-stylegan上找到。
translated by 谷歌翻译
基于能量的模型(EBMS)最近成功地代表了少量图像的复杂分布。然而,对它们的抽样需要昂贵的马尔可夫链蒙特卡罗(MCMC)迭代在高维像素空间中缓慢混合。与EBMS不同,变形AutoEncoders(VAES)快速生成样本,并配备潜在的空间,使得数据歧管的快速遍历。然而,VAE倾向于将高概率密度分配到实际数据分布之外的数据空间中的区域,并且经常在产生清晰图像时失败。在本文中,我们提出了VAE的一个共生组成和ebm的vaebm,提供了两个世界的eBM。 VAEBM使用最先进的VAE捕获数据分布的整体模式结构,它依赖于其EBM组件,以明确地从模型中排除非数据样区域并优化图像样本。此外,VAEBM中的VAE组件允许我们通过在VAE的潜空间中重新处理它们来加速MCMC更新。我们的实验结果表明,VAEBM在几个基准图像数据集上以大量边距开辟了最先进的VAES和EBMS。它可以产生高于256 $ \倍的高质量图像,使用短MCMC链。我们还证明了VAEBM提供了完整的模式覆盖范围,并在分配外检测中表现良好。源代码可在https://github.com/nvlabs/vaebm上获得
translated by 谷歌翻译
随着几个行业正在朝着建模大规模的3D虚拟世界迈进,因此需要根据3D内容的数量,质量和多样性来扩展的内容创建工具的需求变得显而易见。在我们的工作中,我们旨在训练Parterant 3D生成模型,以合成纹理网格,可以通过3D渲染引擎直接消耗,因此立即在下游应用中使用。 3D生成建模的先前工作要么缺少几何细节,因此在它们可以生成的网格拓扑中受到限制,通常不支持纹理,或者在合成过程中使用神经渲染器,这使得它们在常见的3D软件中使用。在这项工作中,我们介绍了GET3D,这是一种生成模型,该模型直接生成具有复杂拓扑,丰富几何细节和高保真纹理的显式纹理3D网格。我们在可区分的表面建模,可区分渲染以及2D生成对抗网络中桥接了最新成功,以从2D图像集合中训练我们的模型。 GET3D能够生成高质量的3D纹理网格,从汽车,椅子,动物,摩托车和人类角色到建筑物,对以前的方法进行了重大改进。
translated by 谷歌翻译
深度生成模型的最新进展导致了3D形状合成的巨大进展。虽然现有模型能够合成表示为体素,点云或隐式功能的形状,但这些方法仅间接强制执行最终3D形状表面的合理性。在这里,我们提出了一种直接将对抗训练施加到物体表面的3D形状合成框架(Surfgen)。我们的方法使用可分解的球面投影层来捕获并表示隐式3D发生器的显式零IsoSurface作为在单元球上定义的功能。通过在对手设置中用球形CNN处理3D对象表面的球形表示,我们的发电机可以更好地学习自然形状表面的统计数据。我们在大规模形状数据集中评估我们的模型,并证明了端到端训练的模型能够产生具有不同拓扑的高保真3D形状。
translated by 谷歌翻译
基于分数的生成模型(SGMS)最近在样品质量和分配覆盖范围内表现出令人印象深刻的结果。但是,它们通常直接应用于数据空间,并且通常需要数千个网络评估来采样。在这里,我们提出了基于潜在的分数的生成模型(LSGM),这是一种在潜在空间中培训SGM的新方法,依赖于变分性AutoEncoder框架。从数据移动到潜伏空间允许我们培训更具表现力的生成模型,将SGMS应用于非连续数据,并在较小的空间中学习更顺畅的SGM,导致更少的网络评估和更快的采样。要以可扩展且稳定的方式启用培训LSGMS端到端,我们(i)我们(i)引入了适合于LSGM设置的新分数匹配目标,(ii)提出了一个新颖的分数函数参数化,允许SGM专注于关于简单正常的目标分布的不匹配,(III)分析了多种技术,用于减少训练目标的方差。 LSGM在CIFAR-10上获得最先进的FID分数为2.10,优先表现出此数据集的所有现有生成结果。在Celeba-HQ-256上,LSGM在样品质量上与先前的SGMS相同,同时以两个数量级的采样时间表现出来。在模拟二进制图像中,LSGM在二值化omniglot数据集上实现了最先进的可能性。我们的项目页面和代码可以在https://nvlabs.github.io/lsgm找到。
translated by 谷歌翻译
DeNoising扩散模型代表了计算机视觉中最新的主题,在生成建模领域表现出了显着的结果。扩散模型是一个基于两个阶段的深层生成模型,一个正向扩散阶段和反向扩散阶段。在正向扩散阶段,通过添加高斯噪声,输入数据在几个步骤中逐渐受到干扰。在反向阶段,模型的任务是通过学习逐步逆转扩散过程来恢复原始输入数据。尽管已知的计算负担,即由于采样过程中涉及的步骤数量,扩散模型对生成样品的质量和多样性得到了广泛赞赏。在这项调查中,我们对视觉中应用的denoising扩散模型的文章进行了全面综述,包括该领域的理论和实际贡献。首先,我们识别并介绍了三个通用扩散建模框架,这些框架基于扩散概率模型,噪声调节得分网络和随机微分方程。我们进一步讨论了扩散模型与其他深层生成模型之间的关系,包括变异自动编码器,生成对抗网络,基于能量的模型,自回归模型和正常流量。然后,我们介绍了计算机视觉中应用的扩散模型的多角度分类。最后,我们说明了扩散模型的当前局限性,并设想了一些有趣的未来研究方向。
translated by 谷歌翻译