神经科学研究表明，大脑编码视觉内容并将信息嵌入神经活动中。最近，深度学习技术通过将大脑活动映射到使用生成的对抗网络（GAN）来刺激来解决视觉重建的尝试。但是，这些研究都没有考虑图像空间中潜在代码的语义含义。省略语义信息可能会限制性能。在这项研究中，我们提出了一个新框架，以从功能磁共振成像（fMRI）数据中重建面部图像。使用此框架，首先将GAN倒置用于训练图像编码器以在图像空间中提取潜在代码，然后使用线性转换将其桥接到fMRI数据中。遵循从fMRI数据使用属性分类器确定的属性，确定操纵属性的方向，属性操纵器调整了潜在代码，以提高可见图像和重建图像之间的一致性。我们的实验结果表明，提出的框架实现了两个目标：（1）从fMRI数据中重建清晰的面部图像，以及（2）保持语义特征的一致性。

Although Generative Adversarial Networks (GANs) have made significant progress in face synthesis, there lacks enough understanding of what GANs have learned in the latent representation to map a random code to a photo-realistic image. In this work, we propose a framework called InterFaceGAN to interpret the disentangled face representation learned by the state-of-the-art GAN models and study the properties of the facial semantics encoded in the latent space. We first find that GANs learn various semantics in some linear subspaces of the latent space. After identifying these subspaces, we can realistically manipulate the corresponding facial attributes without retraining the model. We then conduct a detailed study on the correlation between different semantics and manage to better disentangle them via subspace projection, resulting in more precise control of the attribute manipulation. Besides manipulating the gender, age, expression, and presence of eyeglasses, we can even alter the face pose and fix the artifacts accidentally made by GANs. Furthermore, we perform an in-depth face identity analysis and a layer-wise analysis to evaluate the editing results quantitatively. Finally, we apply our approach to real face editing by employing GAN inversion approaches and explicitly training feed-forward models based on the synthetic data established by InterFaceGAN. Extensive experimental results suggest that learning to synthesize faces spontaneously brings a disentangled and controllable face representation.

Figure 1: Manipulating various facial attributes through varying the latent codes of a well-trained GAN model. The first column shows the original synthesis from PGGAN [21], while each of the other columns shows the results of manipulating a specific attribute.

事实证明，通过倒转和操纵与输入真实图像相对应的潜在代码，生成的对抗网络（GAN）对于图像编辑非常有效。这种编辑属性来自潜在空间的分离性质。在本文中，我们确定面部属性分离不是最佳的，因此依靠线性属性分离的面部编辑是有缺陷的。因此，我们建议通过监督改善语义分解。我们的方法包括使用归一化流量学习代理潜在表示，我们证明这会为面部图像编辑提供更有效的空间。

Recent work has shown that a variety of semantics emerge in the latent space of Generative Adversarial Networks (GANs) when being trained to synthesize images. However, it is difficult to use these learned semantics for real image editing. A common practice of feeding a real image to a trained GAN generator is to invert it back to a latent code. However, existing inversion methods typically focus on reconstructing the target image by pixel values yet fail to land the inverted code in the semantic domain of the original latent space. As a result, the reconstructed image cannot well support semantic editing through varying the inverted code. To solve this problem, we propose an in-domain GAN inversion approach, which not only faithfully reconstructs the input image but also ensures the inverted code to be semantically meaningful for editing. We first learn a novel domain-guided encoder to project a given image to the native latent space of GANs. We then propose domain-regularized optimization by involving the encoder as a regularizer to fine-tune the code produced by the encoder and better recover the target image. Extensive experiments suggest that our inversion method achieves satisfying real image reconstruction and more importantly facilitates various image editing tasks, significantly outperforming start-of-the-arts. 1

尽管在预验证的GAN模型的潜在空间中表现出的编辑能力，但倒置现实世界的图像被陷入困境，即重建不能忠于原始输入。这样做的主要原因是，训练和现实世界数据之间的分布未对准，因此，对于真实图像编辑而言，它不稳定。在本文中，我们提出了一个基于GAN的新型编辑框架，以通过组成分解范式解决室外反转问题。特别是，在构图阶段，我们引入了一个差分激活模块，用于从全局角度\ ie（IE）检测语义变化，这是编辑和未编辑图像的特征之间的相对差距。借助生成的diff-cam掩模，配对的原始图像和编辑图像可以直观地进行粗糙的重建。这样，几乎整体可以生存属性，而这种中间结果的质量仍然受到不可避免的幽灵效果的限制。因此，在分解阶段，我们进一步提出了一个基于GAN的基于GAN的DEGHOSTING网络，用于将最终的精细编辑图像与粗糙重建分开。在定性和定量评估方面，广泛的实验比最新方法具有优势。我们方法的鲁棒性和灵活性在两个属性和多属性操作的方案上也得到了验证。

随着脑成像技术和机器学习工具的出现，很多努力都致力于构建计算模型来捕获人脑中的视觉信息的编码。最具挑战性的大脑解码任务之一是通过功能磁共振成像（FMRI）测量的脑活动的感知自然图像的精确重建。在这项工作中，我们调查了来自FMRI的自然图像重建的最新学习方法。我们在架构设计，基准数据集和评估指标方面检查这些方法，并在标准化评估指标上呈现公平的性能评估。最后，我们讨论了现有研究的优势和局限，并提出了潜在的未来方向。

Our goal with this survey is to provide an overview of the state of the art deep learning technologies for face generation and editing. We will cover popular latest architectures and discuss key ideas that make them work, such as inversion, latent representation, loss functions, training procedures, editing methods, and cross domain style transfer. We particularly focus on GAN-based architectures that have culminated in the StyleGAN approaches, which allow generation of high-quality face images and offer rich interfaces for controllable semantics editing and preserving photo quality. We aim to provide an entry point into the field for readers that have basic knowledge about the field of deep learning and are looking for an accessible introduction and overview.

尽管使用StyleGan进行语义操纵的最新进展，但对真实面孔的语义编辑仍然具有挑战性。 $ W $空间与$ W $+空间之间的差距需要重建质量与编辑质量之间的不良权衡。为了解决这个问题，我们建议通过用基于注意的变压器代替Stylegan映射网络中的完全连接的层来扩展潜在空间。这种简单有效的技术将上述两个空间整合在一起，并将它们转换为一个名为$ W $ ++的新的潜在空间。我们的修改后的Stylegan保持了原始StyleGan的最新一代质量，并具有中等程度的多样性。但更重要的是，提议的$ W $ ++空间在重建质量和编辑质量方面都取得了卓越的性能。尽管有这些显着优势，但我们的$ W $ ++空间支持现有的反转算法和编辑方法，仅由于其与$ w/w $+空间的结构相似性，因此仅可忽略不计的修改。 FFHQ数据集上的广泛实验证明，我们提出的$ W $ ++空间显然比以前的$ w/w $+空间更可取。该代码可在https://github.com/anonsubm2021/transstylegan上公开提供。

在本文中，我们调查了一项开放的研究任务，该任务是从单个2D GAN产生人体面部且没有3D监督的3D卡通面部形状，在那里我们还可以操纵3D形状的面部表情。为此，我们发现了Stylegan潜在空间的语义含义，因此我们能够通过控制潜在代码来产生各种表达式，姿势和照明的面部图像。具体而言，我们首先对卡通数据集中预验证的Stylegan脸部模型进行了修复。通过将相同的潜在代码喂入面部和卡通生成模型，我们的目标是实现从2D人脸图像到卡通风格的化身的翻译。然后，我们发现了甘恩潜在空间的语义方向，以试图在保留原始身份的同时改变面部表情。由于我们没有任何针对卡通脸的3D注释，因此我们操纵潜在代码以生成具有不同姿势和照明的图像，以便我们可以重建3D卡通脸部形状。我们在定性和定量上验证了方法在三个卡通数据集上的疗效。

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。

Facial attribute editing aims to manipulate single or multiple attributes of a face image, i.e., to generate a new face with desired attributes while preserving other details. Recently, generative adversarial net (GAN) and encoder-decoder architecture are usually incorporated to handle this task with promising results. Based on the encoder-decoder architecture, facial attribute editing is achieved by decoding the latent representation of the given face conditioned on the desired attributes. Some existing methods attempt to establish an attributeindependent latent representation for further attribute editing. However, such attribute-independent constraint on the latent representation is excessive because it restricts the capacity of the latent representation and may result in information loss, leading to over-smooth and distorted generation. Instead of imposing constraints on the latent representation, in this work we apply an attribute classification constraint to the generated image to just guarantee the correct change of desired attributes, i.e., to "change what you want". Meanwhile, the reconstruction learning is introduced to preserve attribute-excluding details, in other words, to "only change what you want". Besides, the adversarial learning is employed for visually realistic editing. These three components cooperate with each other forming an effective framework for high quality facial attribute editing, referred as AttGAN. Furthermore, our method is also directly applicable for attribute intensity control and can be naturally extended for attribute style manipulation. Experiments on CelebA dataset show that our method outperforms the state-of-the-arts on realistic attribute editing with facial details well preserved.

Recent 3D-aware GANs rely on volumetric rendering techniques to disentangle the pose and appearance of objects, de facto generating entire 3D volumes rather than single-view 2D images from a latent code. Complex image editing tasks can be performed in standard 2D-based GANs (e.g., StyleGAN models) as manipulation of latent dimensions. However, to the best of our knowledge, similar properties have only been partially explored for 3D-aware GAN models. This work aims to fill this gap by showing the limitations of existing methods and proposing LatentSwap3D, a model-agnostic approach designed to enable attribute editing in the latent space of pre-trained 3D-aware GANs. We first identify the most relevant dimensions in the latent space of the model controlling the targeted attribute by relying on the feature importance ranking of a random forest classifier. Then, to apply the transformation, we swap the top-K most relevant latent dimensions of the image being edited with an image exhibiting the desired attribute. Despite its simplicity, LatentSwap3D provides remarkable semantic edits in a disentangled manner and outperforms alternative approaches both qualitatively and quantitatively. We demonstrate our semantic edit approach on various 3D-aware generative models such as pi-GAN, GIRAFFE, StyleSDF, MVCGAN, EG3D and VolumeGAN, and on diverse datasets, such as FFHQ, AFHQ, Cats, MetFaces, and CompCars. The project page can be found: \url{https://enisimsar.github.io/latentswap3d/}.

由于GaN潜在空间的勘探和利用，近年来，现实世界的图像操纵实现了奇妙的进展。 GaN反演是该管道的第一步，旨在忠实地将真实图像映射到潜在代码。不幸的是，大多数现有的GaN反演方法都无法满足下面列出的三个要求中的至少一个：重建质量，可编辑性和快速推断。我们在本研究中提出了一种新的两阶段策略，同时适合所有要求。在第一阶段，我们训练编码器将输入图像映射到StyleGan2 $ \ Mathcal {W} $ - 空间，这被证明具有出色的可编辑性，但重建质量较低。在第二阶段，我们通过利用一系列HyperNetWorks来补充初始阶段的重建能力以在反转期间恢复缺失的信息。这两个步骤互相补充，由于Hypernetwork分支和由于$ \ Mathcal {W} $ - 空间中的反转，因此由于HyperNetwork分支和优异的可编辑性而相互作用。我们的方法完全是基于编码器的，导致极快的推断。关于两个具有挑战性的数据集的广泛实验证明了我们方法的优越性。

A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images. In order to identify such latent dimensions for image editing, previous methods typically annotate a collection of synthesized samples and train linear classifiers in the latent space. However, they require a clear definition of the target attribute as well as the corresponding manual annotations, limiting their applications in practice. In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner. In particular, we take a closer look into the generation mechanism of GANs and further propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights. With a lightning-fast implementation, our approach is capable of not only finding semantically meaningful dimensions comparably to the state-of-the-art supervised methods, but also resulting in far more versatile concepts across multiple GAN models trained on a wide range of datasets. 1

我们提出了Vecgan，这是一个图像到图像翻译框架，用于带有可解释潜在方向的面部属性编辑。面部属性编辑任务面临着精确属性编辑的挑战，具有可控的强度和图像的其他属性的保存。对于此目标，我们通过潜在空间分解设计属性编辑，对于每个属性，我们学习了与其他属性正交的线性方向。另一个组件是变化的可控强度，标量值。在我们的框架中，可以通过投影从参考图像中对此标量进行采样或编码。我们的工作灵感来自固定预验证的gan的潜在空间分解作品。但是，尽管这些模型无法进行端到端训练，并难以精确编辑编码的图像，但Vecgan受到了端到端的培训，用于图像翻译任务，并成功地编辑了属性，同时保留了其他属性。我们的广泛实验表明，vecgan对本地和全球编辑的最先进进行了重大改进。

扩散概率模型（DPMS）在竞争对手GANS的图像生成中取得了显着的质量。但与GAN不同，DPMS使用一组缺乏语义含义的一组潜在变量，并且不能作为其他任务的有用表示。本文探讨了使用DPMS进行表示学习的可能性，并寻求通过自动编码提取输入图像的有意义和可解码的表示。我们的主要思想是使用可学习的编码器来发现高级语义，以及DPM作为用于建模剩余随机变化的解码器。我们的方法可以将任何图像编码为两部分潜在的代码，其中第一部分是语义有意义和线性的，第二部分捕获随机细节，允许接近精确的重建。这种功能使当前箔基于GaN的方法的挑战性应用，例如实际图像上的属性操作。我们还表明，这两级编码可提高去噪效率，自然地涉及各种下游任务，包括几次射击条件采样。

尽管最近通过生成对抗网络（GAN）操纵面部属性最近取得了非常成功的成功，但在明确控制姿势，表达，照明等特征的明确控制方面仍然存在一些挑战。最近的方法通过结合2D生成模型来实现对2D图像的明确控制和3dmm。但是，由于3DMM缺乏现实主义和纹理重建的清晰度，因此合成图像与3DMM的渲染图像之间存在域间隙。由于渲染的3DMM图像仅包含面部区域，因此直接计算这两个域之间的损失是不理想的，因此训练有素的模型将是偏差的。在这项研究中，我们建议通过控制3DMM的参数来明确编辑验证样式的潜在空间。为了解决域间隙问题，我们提出了一个名为“地图和编辑”的新网络，以及一种简单但有效的属性编辑方法，以避免渲染和合成图像之间的直接损失计算。此外，由于我们的模型可以准确地生成多视图的面部图像，而身份保持不变。作为副产品，结合可见性掩模，我们提出的模型还可以生成质地丰富和高分辨率的紫外面部纹理。我们的模型依赖于验证的样式，并且提出的模型以自我监督的方式进行了训练，而无需任何手动注释或数据集训练。

We present a novel image inversion framework and a training pipeline to achieve high-fidelity image inversion with high-quality attribute editing. Inverting real images into StyleGAN's latent space is an extensively studied problem, yet the trade-off between the image reconstruction fidelity and image editing quality remains an open challenge. The low-rate latent spaces are limited in their expressiveness power for high-fidelity reconstruction. On the other hand, high-rate latent spaces result in degradation in editing quality. In this work, to achieve high-fidelity inversion, we learn residual features in higher latent codes that lower latent codes were not able to encode. This enables preserving image details in reconstruction. To achieve high-quality editing, we learn how to transform the residual features for adapting to manipulations in latent codes. We train the framework to extract residual features and transform them via a novel architecture pipeline and cycle consistency losses. We run extensive experiments and compare our method with state-of-the-art inversion methods. Qualitative metrics and visual comparisons show significant improvements. Code: https://github.com/hamzapehlivan/StyleRes

生成对抗网络（GAN）已广泛应用于建模各种图像分布。然而，尽管具有令人印象深刻的应用，但甘恩（Gans）中潜在空间的结构在很大程度上仍然是一个黑框，使其可控的一代问题是一个开放的问题，尤其是当图像分布中存在不同语义属性之间的虚假相关性时。为了解决此问题，以前的方法通常会学习控制图像空间中语义属性的线性方向或单个通道。但是，他们通常会遭受不完美的分解，或者无法获得多向控制。在这项工作中，根据上述挑战，我们提出了一种新的方法，可以发现非线性控件，该方法基于学识渊博的gan潜在空间中的梯度信息，可以实现多个方向的操作以及有效的分解。更具体地说，我们首先通过从对属性分别训练的分类网络中遵循梯度来学习插值方向，然后通过专门控制针对目标属性在学习的方向上激活目标属性的通道来导航潜在空间。从经验上讲，借助小型培训数据，我们的方法能够获得对各种双向和多方向属性的细粒度控制，并且我们展示了其实现分离的能力，其能力明显优于先进方法。定性和定量。