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/

Video generation requires synthesizing consistent and persistent frames with dynamic content over time. This work investigates modeling the temporal relations for composing video with arbitrary length, from a few frames to even infinite, using generative adversarial networks (GANs). First, towards composing adjacent frames, we show that the alias-free operation for single image generation, together with adequately pre-learned knowledge, brings a smooth frame transition without compromising the per-frame quality. Second, by incorporating the temporal shift module (TSM), originally designed for video understanding, into the discriminator, we manage to advance the generator in synthesizing more consistent dynamics. Third, we develop a novel B-Spline based motion representation to ensure temporal smoothness to achieve infinite-length video generation. It can go beyond the frame number used in training. A low-rank temporal modulation is also proposed to alleviate repeating contents for long video generation. We evaluate our approach on various datasets and show substantial improvements over video generation baselines. Code and models will be publicly available at https://genforce.github.io/StyleSV.

Generative adversarial network (GAN) is formulated as a two-player game between a generator (G) and a discriminator (D), where D is asked to differentiate whether an image comes from real data or is produced by G. Under such a formulation, D plays as the rule maker and hence tends to dominate the competition. Towards a fairer game in GANs, we propose a new paradigm for adversarial training, which makes G assign a task to D as well. Specifically, given an image, we expect D to extract representative features that can be adequately decoded by G to reconstruct the input. That way, instead of learning freely, D is urged to align with the view of G for domain classification. Experimental results on various datasets demonstrate the substantial superiority of our approach over the baselines. For instance, we improve the FID of StyleGAN2 from 4.30 to 2.55 on LSUN Bedroom and from 4.04 to 2.82 on LSUN Church. We believe that the pioneering attempt present in this work could inspire the community with better designed generator-leading tasks for GAN improvement.

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.

通过区分真实和合成样品，鉴别器在训练生成对抗网络（GAN）中起着至关重要的作用。尽管实际数据分布保持不变，但由于发电机的发展，合成分布一直变化，从而影响鉴别器的BI分类任务的相应变化。我们认为，对其容量进行即时调整的歧视者可以更好地适应这种时间变化的任务。一项全面的实证研究证实，所提出的培训策略称为Dynamicd，改善了合成性能，而不会产生任何其他计算成本或培训目标。在不同的数据制度下开发了两个容量调整方案，用于培训gan：i）给定足够数量的培训数据，歧视者从逐渐增加的学习能力中受益，ii）ii）当培训数据受到限制时，逐渐减少层宽度的宽度减轻。歧视者的过度问题。在一系列数据集上进行的2D和3D感知图像合成任务的实验证实了我们的动力学的普遍性以及对基准的实质性改进。此外，Dynamicd与其他歧视器改进方法（包括数据增强，正规化器和预训练）具有协同作用，并且在将学习gans合并时会带来连续的性能增长。

近年来，由于其在数字人物，角色产生和动画中的广泛应用，人们对3D人脸建模的兴趣越来越大。现有方法压倒性地强调了对面部的外部形状，质地和皮肤特性建模，而忽略了内部骨骼结构和外观之间的固有相关性。在本文中，我们使用学习的参数面部发电机提出了雕塑家，具有骨骼一致性的3D面部创作，旨在通过混合参数形态表示轻松地创建解剖上正确和视觉上令人信服的面部模型。雕塑家的核心是露西（Lucy），这是与整形外科医生合作的第一个大型形状面部脸部数据集。我们的Lucy数据集以最古老的人类祖先之一的化石命名，其中包含正牙手术前后全人头的高质量计算机断层扫描（CT）扫描，这对于评估手术结果至关重要。露西（Lucy）由144次扫描，分别对72名受试者（31名男性和41名女性）组成，其中每个受试者进行了两次CT扫描，并在恐惧后手术中进行了两次CT扫描。根据我们的Lucy数据集，我们学习了一个新颖的骨骼一致的参数面部发电机雕塑家，它可以创建独特而细微的面部特征，以帮助定义角色，同时保持生理声音。我们的雕塑家通过将3D脸的描绘成形状混合形状，姿势混合形状和面部表达混合形状，共同在统一数据驱动的框架下共同建模头骨，面部几何形状和面部外观。与现有方法相比，雕塑家在面部生成任务中保留了解剖学正确性和视觉现实主义。最后，我们展示了雕塑家在以前看不见的各种花式应用中的鲁棒性和有效性。

反转生成对抗网络（GAN）可以使用预训练的发电机来促进广泛的图像编辑任务。现有方法通常采用gan的潜在空间作为反转空间，但观察到空间细节的恢复不足。在这项工作中，我们建议涉及发电机的填充空间，以通过空间信息补充潜在空间。具体来说，我们替换具有某些实例感知系数的卷积层中使用的恒定填充（例如，通常为零）。通过这种方式，可以适当地适当地适应了预训练模型中假定的归纳偏差以适合每个单独的图像。通过学习精心设计的编码器，我们设法在定性和定量上提高了反演质量，超过了现有的替代方案。然后，我们证明了这样的空间扩展几乎不会影响天然甘纳的歧管，因此我们仍然可以重复使用甘斯（Gans）对各种下游应用学到的先验知识。除了在先前的艺术中探讨的编辑任务外，我们的方法还可以进行更灵活的图像操纵，例如对面部轮廓和面部细节的单独控制，并启用一种新颖的编辑方式，用户可以高效地自定义自己的操作。

尽管在生成对抗网络（GAN）的潜在空间中，语义发现迅速发展，但现有方法要么仅限于找到全局属性，要么依靠许多细分掩码来识别本地属性。在这项工作中，我们提出了一种高效的算法，以分解甘恩学到的关于任意图像区域的潜在语义。具体而言，我们重新审视了预先训练的gan的局部操纵任务，并将基于区域的语义发现作为双重优化问题。通过适当定义的广义雷利商，我们设法解决了这个问题，而无需任何注释或培训。对各种最先进的GAN模型的实验结果证明了我们的方法的有效性，以及它优于先前艺术在精确控制，区域鲁棒性，实施速度和使用简单性方面的优势。

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。

由于数据注释的高成本，半监督行动识别是一个具有挑战性的，但重要的任务是。这个问题的常见方法是用伪标签分配未标记的数据，然后将其作为训练中的额外监督。通常在最近的工作中，通过在标记数据上训练模型来获得伪标签，然后使用模型的自信预测来教授自己。在这项工作中，我们提出了一种更有效的伪标签方案，称为跨模型伪标记（CMPL）。具体地，除了主要骨干内，我们还介绍轻量级辅助网络，并要求他们互相预测伪标签。我们观察到，由于其不同的结构偏差，这两种模型倾向于学习来自同一视频剪辑的互补表示。因此，通过利用跨模型预测作为监督，每个模型都可以受益于其对应物。对不同数据分区协议的实验表明我们对现有替代方案框架的重大改进。例如，CMPL在Kinetics-400和UCF-101上实现了17.6 \％$ 17.6 \％$ 25.1 \％$ 25.使用RGB模态和1 \％$标签数据，优于我们的基线模型，FIXMATCT，以$ 9.0 \％ $和10.3美元\％$。