Deep generative models allow for photorealistic image synthesis at high resolutions. But for many applications, this is not enough: content creation also needs to be controllable. While several recent works investigate how to disentangle underlying factors of variation in the data, most of them operate in 2D and hence ignore that our world is three-dimensional. Further, only few works consider the compositional nature of scenes. Our key hypothesis is that incorporating a compositional 3D scene representation into the generative model leads to more controllable image synthesis. Representing scenes as compositional generative neural feature fields allows us to disentangle one or multiple objects from the background as well as individual objects' shapes and appearances while learning from unstructured and unposed image collections without any additional supervision. Combining this scene representation with a neural rendering pipeline yields a fast and realistic image synthesis model. As evidenced by our experiments, our model is able to disentangle individual objects and allows for translating and rotating them in the scene as well as changing the camera pose.

While 2D generative adversarial networks have enabled high-resolution image synthesis, they largely lack an understanding of the 3D world and the image formation process. Thus, they do not provide precise control over camera viewpoint or object pose. To address this problem, several recent approaches leverage intermediate voxel-based representations in combination with differentiable rendering. However, existing methods either produce low image resolution or fall short in disentangling camera and scene properties, e.g., the object identity may vary with the viewpoint. In this paper, we propose a generative model for radiance fields which have recently proven successful for novel view synthesis of a single scene. In contrast to voxelbased representations, radiance fields are not confined to a coarse discretization of the 3D space, yet allow for disentangling camera and scene properties while degrading gracefully in the presence of reconstruction ambiguity. By introducing a multi-scale patch-based discriminator, we demonstrate synthesis of high-resolution images while training our model from unposed 2D images alone. We systematically analyze our approach on several challenging synthetic and real-world datasets. Our experiments reveal that radiance fields are a powerful representation for generative image synthesis, leading to 3D consistent models that render with high fidelity.

The 3D-aware image synthesis focuses on conserving spatial consistency besides generating high-resolution images with fine details. Recently, Neural Radiance Field (NeRF) has been introduced for synthesizing novel views with low computational cost and superior performance. While several works investigate a generative NeRF and show remarkable achievement, they cannot handle conditional and continuous feature manipulation in the generation procedure. In this work, we introduce a novel model, called Class-Continuous Conditional Generative NeRF ($\text{C}^{3}$G-NeRF), which can synthesize conditionally manipulated photorealistic 3D-consistent images by projecting conditional features to the generator and the discriminator. The proposed $\text{C}^{3}$G-NeRF is evaluated with three image datasets, AFHQ, CelebA, and Cars. As a result, our model shows strong 3D-consistency with fine details and smooth interpolation in conditional feature manipulation. For instance, $\text{C}^{3}$G-NeRF exhibits a Fr\'echet Inception Distance (FID) of 7.64 in 3D-aware face image synthesis with a $\text{128}^{2}$ resolution. Additionally, we provide FIDs of generated 3D-aware images of each class of the datasets as it is possible to synthesize class-conditional images with $\text{C}^{3}$G-NeRF.

制作生成模型3D感知桥梁2D图像空间和3D物理世界仍然挑战。最近尝试用神经辐射场（NERF）配备生成的对抗性网络（GAN），其将3D坐标映射到像素值，作为3D之前。然而，nerf中的隐式功能具有一个非常局部的接收领域，使得发电机难以意识到全局结构。与此同时，NERF建立在体积渲染上，这可能太昂贵，无法产生高分辨率结果，提高优化难度。为了减轻这两个问题，我们通过明确学习结构表示和纹理表示，向高保真3D感知图像综合提出了一种作为Volumegan称为Volumegan的新颖框架。我们首先学习一个特征卷来表示底层结构，然后使用类似NERF的模型转换为特征字段。特征字段进一步累积到作为纹理表示的2D特征图中，然后是用于外观合成的神经渲染器。这种设计使得能够独立控制形状和外观。广泛的数据集的大量实验表明，我们的方法比以前的方法实现了足够更高的图像质量和更好的3D控制。

最先进的3D感知生成模型依赖于基于坐标的MLP来参数化3D辐射场。在证明令人印象深刻的结果的同时，请查询每个沿每个射线样品的MLP，都会导致渲染缓慢。因此，现有方法通常会呈现低分辨率特征图，并通过UPSMPLING网络处理以获取最终图像。尽管有效，神经渲染通常纠缠于观点和内容，从而改变摄像头会导致几何或外观的不必要变化。在基于体素的新型视图合成中的最新结果中，我们研究了本文中稀疏体素电网表示的快速和3D一致生成建模的实用性。我们的结果表明，当将稀疏体素电网与渐进式生长，自由空间修剪和适当的正则化结合时，单层MLP确实可以被3D卷积代替。为了获得场景的紧凑表示并允许缩放到更高的体素分辨率，我们的模型将前景对象（以3D模型）从背景（以2D模型建模）中。与现有方法相反，我们的方法仅需要单个正向通行证来生成完整的3D场景。因此，它允许从任意观点呈现有效渲染，同时以高视觉保真度产生3D一致的结果。

Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects. This work presents DisCoScene: a 3Daware generative model for high-quality and controllable scene synthesis. The key ingredient of our method is a very abstract object-level representation (i.e., 3D bounding boxes without semantic annotation) as the scene layout prior, which is simple to obtain, general to describe various scene contents, and yet informative to disentangle objects and background. Moreover, it serves as an intuitive user control for scene editing. Based on such a prior, the proposed model spatially disentangles the whole scene into object-centric generative radiance fields by learning on only 2D images with the global-local discrimination. Our model obtains the generation fidelity and editing flexibility of individual objects while being able to efficiently compose objects and the background into a complete scene. We demonstrate state-of-the-art performance on many scene datasets, including the challenging Waymo outdoor dataset. Project page: https://snap-research.github.io/discoscene/

We have witnessed rapid progress on 3D-aware image synthesis, leveraging recent advances in generative visual models and neural rendering. Existing approaches however fall short in two ways: first, they may lack an underlying 3D representation or rely on view-inconsistent rendering, hence synthesizing images that are not multi-view consistent; second, they often depend upon representation network architectures that are not expressive enough, and their results thus lack in image quality. We propose a novel generative model, named Periodic Implicit Generative Adversarial Networks (π-GAN or pi-GAN), for high-quality 3D-aware image synthesis. π-GAN leverages neural representations with periodic activation functions and volumetric rendering to represent scenes as view-consistent radiance fields. The proposed approach obtains state-of-the-art results for 3D-aware image synthesis with multiple real and synthetic datasets.

2 Lambda Labs 3 Twitter Figure 1. HoloGAN learns to separate pose from identity (shape and appearance) only from unlabelled 2D images without sacrificing the visual fidelity of the generated images. All results shown here are sampled from HoloGAN for the same identities in each row but in different poses.

生成模型已成为许多图像合成和编辑任务的基本构件。该领域的最新进展还使得能够生成具有多视图或时间一致性的高质量3D或视频内容。在我们的工作中，我们探索了学习无条件生成3D感知视频的4D生成对抗网络（GAN）。通过将神经隐式表示与时间感知歧视器相结合，我们开发了一个GAN框架，该框架仅通过单眼视频进行监督的3D视频。我们表明，我们的方法学习了可分解的3D结构和动作的丰富嵌入，这些结构和动作可以使时空渲染的新视觉效果，同时以与现有3D或视频gan相当的质量产生图像。

使用单视图2D照片仅集合，无监督的高质量多视图 - 一致的图像和3D形状一直是一个长期存在的挑战。现有的3D GAN是计算密集型的，也是没有3D-一致的近似;前者限制了所生成的图像的质量和分辨率，并且后者对多视图一致性和形状质量产生不利影响。在这项工作中，我们提高了3D GAN的计算效率和图像质量，而无需依赖这些近似。为此目的，我们介绍了一种表现力的混合明确隐式网络架构，与其他设计选择一起，不仅可以实时合成高分辨率多视图一致图像，而且还产生高质量的3D几何形状。通过解耦特征生成和神经渲染，我们的框架能够利用最先进的2D CNN生成器，例如Stylega2，并继承它们的效率和表现力。在其他实验中，我们展示了与FFHQ和AFHQ猫的最先进的3D感知合成。

We introduce 3inGAN, an unconditional 3D generative model trained from 2D images of a single self-similar 3D scene. Such a model can be used to produce 3D "remixes" of a given scene, by mapping spatial latent codes into a 3D volumetric representation, which can subsequently be rendered from arbitrary views using physically based volume rendering. By construction, the generated scenes remain view-consistent across arbitrary camera configurations, without any flickering or spatio-temporal artifacts. During training, we employ a combination of 2D, obtained through differentiable volume tracing, and 3D Generative Adversarial Network (GAN) losses, across multiple scales, enforcing realism on both its 3D structure and the 2D renderings. We show results on semi-stochastic scenes of varying scale and complexity, obtained from real and synthetic sources. We demonstrate, for the first time, the feasibility of learning plausible view-consistent 3D scene variations from a single exemplar scene and provide qualitative and quantitative comparisons against recent related methods.

生成辐射场的进步推动了3D感知图像合成的边界。通过观察到3D对象应该从多个观点看起来真实的观察，这些方法将多视图约束引入正则化以从2D图像学习有效的3D辐射场。尽管有了进步，但由于形状彩色模糊，它们通常会缺少准确的3D形状，这限制了它们在下游任务中的适用性。在这项工作中，我们通过提出一种新的阴影引导的生成隐式模型来解决这种模糊性，能够学习持续改进的形状表示。我们的主要洞察力是，在不同的照明条件下，精确的3D形状还应产生逼真的渲染。通过明确地模拟照明和具有各种照明条件的阴影来实现这种多照明约束。通过将合成的图像馈送到鉴别器来导出梯度。为了补偿计算表面法线的额外计算负担，我们进一步通过表面跟踪设计了高效的体积渲染策略，将培训和推理时间分别将培训和推理时间减少了24％和48％。我们在多个数据集上的实验表明，该方法在捕获准确的基础3D形状时实现了光电型3D感知图像合成。我们展示了我们对现有方法的3D形重建的方法的改进性能，并展示了其对图像复兴的适用性。我们的代码将在https://github.com/xingangpan/shadegan发布。

我们提出了一种无监督的方法，用于对铰接对象的3D几何形式表示学习，其中不使用图像置态对或前景口罩进行训练。尽管可以通过现有的3D神经表示的明确姿势控制铰接物体的影像图像，但这些方法需要地面真相3D姿势和前景口罩进行训练，这是昂贵的。我们通过学习GAN培训来学习表示形式来消除这种需求。该发电机经过训练，可以通过对抗训练从随机姿势和潜在向量产生逼真的铰接物体图像。为了避免GAN培训的高计算成本，我们提出了基于三平面的铰接对象的有效神经表示形式，然后为其无监督培训提供了基于GAN的框架。实验证明了我们方法的效率，并表明基于GAN的培训可以在没有配对监督的情况下学习可控的3D表示。

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。

最近已经示出了从2D图像中提取隐式3D表示的生成神经辐射场（GNERF）模型，以产生代表刚性物体的现实图像，例如人面或汽车。然而，他们通常难以产生代表非刚性物体的高质量图像，例如人体，这对许多计算机图形应用具有很大的兴趣。本文提出了一种用于人类图像综合的3D感知语义导向生成模型（3D-SAGGA），其集成了GNERF和纹理发生器。前者学习人体的隐式3D表示，并输出一组2D语义分段掩模。后者将这些语义面部掩模转化为真实的图像，为人类的外观添加了逼真的纹理。如果不需要额外的3D信息，我们的模型可以使用照片现实可控生成学习3D人类表示。我们在Deepfashion DataSet上的实验表明，3D-SAGGAN显着优于最近的基线。

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.

Unsupervised learning with generative models has the potential of discovering rich representations of 3D scenes. While geometric deep learning has explored 3Dstructure-aware representations of scene geometry, these models typically require explicit 3D supervision. Emerging neural scene representations can be trained only with posed 2D images, but existing methods ignore the three-dimensional structure of scenes. We propose Scene Representation Networks (SRNs), a continuous, 3Dstructure-aware scene representation that encodes both geometry and appearance. SRNs represent scenes as continuous functions that map world coordinates to a feature representation of local scene properties. By formulating the image formation as a differentiable ray-marching algorithm, SRNs can be trained end-toend from only 2D images and their camera poses, without access to depth or shape. This formulation naturally generalizes across scenes, learning powerful geometry and appearance priors in the process. We demonstrate the potential of SRNs by evaluating them for novel view synthesis, few-shot reconstruction, joint shape and appearance interpolation, and unsupervised discovery of a non-rigid face model. 1

我们提出Volux-GaN，一种生成框架，以合成3D感知面孔的令人信服的回忆。我们的主要贡献是一种体积的HDRI可发感方法，可以沿着每个3D光线沿着任何所需的HDR环境图累计累积Albedo，漫射和镜面照明贡献。此外，我们展示了使用多个鉴别器监督图像分解过程的重要性。特别是，我们提出了一种数据增强技术，其利用单个图像肖像结合的最近的进步来强制实施一致的几何形状，反照镜，漫射和镜面组分。与其他生成框架的多个实验和比较展示了我们的模型是如何向光电型可致力于的3D生成模型前进的一步。

综合照片 - 现实图像和视频是计算机图形的核心，并且是几十年的研究焦点。传统上，使用渲染算法（如光栅化或射线跟踪）生成场景的合成图像，其将几何形状和材料属性的表示为输入。统称，这些输入定义了实际场景和呈现的内容，并且被称为场景表示（其中场景由一个或多个对象组成）。示例场景表示是具有附带纹理的三角形网格（例如，由艺术家创建），点云（例如，来自深度传感器），体积网格（例如，来自CT扫描）或隐式曲面函数（例如，截短的符号距离）字段）。使用可分辨率渲染损耗的观察结果的这种场景表示的重建被称为逆图形或反向渲染。神经渲染密切相关，并将思想与经典计算机图形和机器学习中的思想相结合，以创建用于合成来自真实观察图像的图像的算法。神经渲染是朝向合成照片现实图像和视频内容的目标的跨越。近年来，我们通过数百个出版物显示了这一领域的巨大进展，这些出版物显示了将被动组件注入渲染管道的不同方式。这种最先进的神经渲染进步的报告侧重于将经典渲染原则与学习的3D场景表示结合的方法，通常现在被称为神经场景表示。这些方法的一个关键优势在于它们是通过设计的3D-一致，使诸如新颖的视点合成捕获场景的应用。除了处理静态场景的方法外，我们还涵盖了用于建模非刚性变形对象的神经场景表示...

以前的纵向图像生成方法大致分为两类：2D GAN和3D感知的GAN。 2D GAN可以产生高保真肖像，但具有低视图一致性。 3D感知GaN方法可以维护查看一致性，但它们所生成的图像不是本地可编辑的。为了克服这些限制，我们提出了FENERF，一个可以生成查看一致和本地可编辑的纵向图像的3D感知生成器。我们的方法使用两个解耦潜码，以在具有共享几何体的空间对齐的3D卷中生成相应的面部语义和纹理。从这种底层3D表示中受益，FENERF可以联合渲染边界对齐的图像和语义掩码，并使用语义掩模通过GaN反转编辑3D音量。我们进一步示出了可以从广泛可用的单手套图像和语义面膜对中学习这种3D表示。此外，我们揭示了联合学习语义和纹理有助于产生更精细的几何形状。我们的实验表明FENERF在各种面部编辑任务中优于最先进的方法。