SalS-GAN

Spectral alignment of multi-temporal cross-sensor images with automated kernel canonical correlation analysis

The inversion of real images into StyleGAN's latent space is a well-studied problem. Nevertheless, applying existing approaches to real-world scenarios remains an open challenge, due to an inherent trade-off between reconstruction and editability: latent space regions which can accurately represent real images typically suffer from degraded semantic control. Recent work proposes to mitigate this trade-off by fine-tuning the generator to add the target image to well-behaved, editable regions of the latent space. While promising, this fine-tuning scheme is impractical for prevalent use as it requires a lengthy training phase for each new image. In this work, we introduce this approach into the realm of encoder-based inversion. We propose HyperStyle, a hypernetwork that learns to modulate StyleGAN's weights to faithfully express a given image in editable regions of the latent space. A naive modulation approach would require training a hypernetwork with over three billion parameters. Through careful network design, we reduce this to be in line with existing encoders. HyperStyle yields reconstructions comparable to those of optimization techniques with the near real-time inference capabilities of encoders. Lastly, we demonstrate HyperStyle's effectiveness on several applications beyond the inversion task, including the editing of out-of-domain images which were never seen during training. Code is available on our project page: https://yuval-alaluf.github.io/hyperstyle/.

Generative models rely on the idea that data can be represented in terms of latent variables which are uncorrelated by definition. Lack of correlation among the latent variable support is important because it suggests that the latent-space manifold is simpler to understand and manipulate than the real-space representation. Many types of generative model are used in deep learning, e.g., variational autoencoders (VAEs) and generative adversarial networks (GANs). Based on the idea that the latent space behaves like a vector space Radford et al. (2015), we ask whether we can expand the latent space representation of our data elements in terms of an orthonormal basis set. Here we propose a method to build a set of linearly independent vectors in the latent space of a trained GAN, which we call quasi-eigenvectors. These quasi-eigenvectors have two key properties: i) They span the latent space, ii) A set of these quasi-eigenvectors map to each of the labeled features one-to-one. We show that in the case of the MNIST image data set, while the number of dimensions in latent space is large by design, 98% of the data in real space map to a sub-domain of latent space of dimensionality equal to the number of labels. We then show how the quasi-eigenvectors can be used for Latent Spectral Decomposition (LSD). We apply LSD to denoise MNIST images. Finally, using the quasi-eigenvectors, we construct rotation matrices in latent space which map to feature transformations in real space. Overall, from quasi-eigenvectors we gain insight regarding the latent space topology.

Learning based single image super-resolution (SISR) for real-world images has been an active research topic yet a challenging task, due to the lack of paired low-resolution (LR) and high-resolution (HR) training images. Most of the existing unsupervised real-world SISR methods adopt a two-stage training strategy by synthesizing realistic LR images from their HR counterparts first, then training the super-resolution (SR) models in a supervised manner. However, the training of image degradation and SR models in this strategy are separate, ignoring the inherent mutual dependency between downscaling and its inverse upscaling process. Additionally, the ill-posed nature of image degradation is not fully considered. In this paper, we propose an image downscaling and SR model dubbed as SDFlow, which simultaneously learns a bidirectional many-to-many mapping between real-world LR and HR images unsupervisedly. The main idea of SDFlow is to decouple image content and degradation information in the latent space, where content information distribution of LR and HR images is matched in a common latent space. Degradation information of the LR images and the high-frequency information of the HR images are fitted to an easy-to-sample conditional distribution. Experimental results on real-world image SR datasets indicate that SDFlow can generate diverse realistic LR and SR images both quantitatively and qualitatively.

This article presents an evolutionary approach for synthetic human portraits generation based on the latent space exploration of a generative adversarial network. The idea is to produce different human face images very similar to a given target portrait. The approach applies StyleGAN2 for portrait generation and FaceNet for face similarity evaluation. The evolutionary search is based on exploring the real-coded latent space of StyleGAN2. The main results over both synthetic and real images indicate that the proposed approach generates accurate and diverse solutions, which represent realistic human portraits. The proposed research can contribute to improving the security of face recognition systems.

A latent space represents data by embedding them in a multidimensional vector space. In this way an abstract estimation of any complex domain could be created. Empirical approach for exploring the latent space generated by known pre-trained model of human face images using a nonlinear dimensionality reduction algorithm is presented in this paper. One aim was to find more detailed entangled features (beard and hair color) between the real images and their representation, in artistic face portrait application. Experimental results showed that sparse vectors in the latent space could be useful to obtain optimal results with relatively low effort. To evaluate our work, we present the results of a survey that was sent to 25 thousand subscribers of the real world application and got around 360 responses. The main goal of the survey was to find some quantitative measurements that can be used in our research.KeywordsLatent space explorationNonlinear dimensionality reductionGenerative adversarial networks (GANs)Industrial survey

Generative adversarial network (GAN)-based models possess superior capability of high-fidelity image synthesis. There are a wide range of semantically meaningful directions in the latent representation space of well-trained GANs, and the corresponding latent space walks are meaningful for semantic controllability in the synthesized images. To explore the underlying organization of a latent space, we propose an unsupervised Density-Preserving Latent Semantics Exploration model (DP-LaSE). The important latent directions are determined by maximizing the variations in intermediate features, while the correlation between the directions is minimized. Considering that latent codes are sampled from a prior distribution, we adopt a density-preserving regularization approach to ensure latent space walks are maintained in iso-density regions, since moving to a higher/lower density region tends to cause unexpected transformations. To further refine semantics-specific transformations, we perform subspace learning over intermediate feature channels, such that the transformations are limited to the most relevant subspaces. Extensive experiments on a variety of benchmark datasets demonstrate that DP-LaSE is able to discover interpretable latent space walks, and specific properties of synthesized images can thus be precisely controlled.

Generation of photo-realistic images, semantic editing and representation learning are only a few of many applications of high-resolution generative models. Recent progress in GANs have established them as an excellent choice for such tasks. However, since they do not provide an inference model, downstream tasks such as classification cannot be easily applied on real images using the GAN latent space. Despite numerous efforts to train an inference model or design an iterative method to invert a pre-trained generator, previous methods are dataset (e.g. human face images) and architecture (e.g. StyleGAN) specific. These methods are nontrivial to extend to novel datasets or architectures. We propose a general framework that is agnostic to architecture and datasets. Our key insight is that, by training the inference and the generative model together, we allow them to adapt to each other and to converge to a better quality model. Our InvGAN, short for Invertible GAN, successfully embeds real images in the latent space of a high quality generative model. This allows us to perform image inpainting, merging, interpolation and online data augmentation. We demonstrate this with extensive qualitative and quantitative experiments.

Training generative models, such as GANs, on a target domain containing limited examples (e.g., 10) can easily result in overfitting. In this work, we seek to utilize a large source domain for pretraining and transfer the diversity information from source to target. We propose to preserve the relative similarities and differences between instances in the source via a novel cross-domain distance consistency loss. To further reduce overfitting, we present an anchor-based strategy to encourage different levels of realism over different regions in the latent space. With extensive results in both photorealistic and non-photorealistic domains, we demonstrate qualitatively and quantitatively that our few-shot model automatically discovers correspondences between source and target domains and generates more diverse and realistic images than previous methods.

Model Inversion (MI) attacks based on Generative Adversarial Networks (GAN) aim to recover private training data from complex deep learning models by searching codes in the latent space. However, this method merely searches in a deterministic latent space, resulting in suboptimal latent codes. Additionally, existing distributional MI schemes assume that an attacker can access the structures and parameters of the target model, which is not always feasible in practice. To address these limitations, this paper proposes a novel Distributional Black-Box Model Inversion (DBB-MI) attack by constructing a probabilistic latent space for searching private data. Specifically, DBB-MI does not require the target model’s parameters or specialized GAN training. Instead, it identifies the latent probability distribution by integrating the output of the target model with multi-agent reinforcement learning techniques. Then, it randomly selects latent codes from the latent probability distribution to uncover private data. As the latent probability distribution closely mirrors the target privacy data in the latent space, the recovered data effectively leaks the privacy of the target model’s training samples. Extensive experiments conducted on diverse datasets and networks demonstrate that our DBB-MI outperforms state-of-the-art MI attacks in terms of attack accuracy, K-nearest neighbor feature distance, and peak signal-to-noise ratio.

This work addresses the problem of discovering, in an unsupervised manner, interpretable paths in the latent space of pretrained GANs, so as to provide an intuitive and easy way of controlling the underlying generative factors. In doing so, it addresses some of the limitations of the state-of-the-art works, namely, a) that they discover directions that are independent of the latent code, i.e., paths that are linear, and b) that their evaluation relies either on visual inspection or on laborious human labeling. More specifically, we propose to learn non-linear warpings on the latent space, each one parametrized by a set of RBF-based latent space warping functions, and where each warping gives rise to a family of non-linear paths via the gradient of the function. Building on the work of [34], that discovers linear paths, we optimize the trainable parameters of the set of RBFs, so as that images that are generated by codes along different paths, are easily distinguishable by a discriminator network. This leads to easily distinguishable image transformations, such as pose and facial expressions in facial images. We show that linear paths can be derived as a special case of our method, and show experimentally that non-linear paths in the latent space lead to steeper, more disentangled and interpretable changes in the image space than in state-of-the art methods, both qualitatively and quantitatively. We make the code and the pretrained models publicly available at: https://github.com/chi0tzp/WarpedGANSpace.

This work addresses the problem of discovering, in an unsupervised manner, interpretable paths in the latent space of pretrained GANs, so as to provide an intuitive and easy way of controlling the underlying generative factors. In doing so, it addresses some of the limitations of the state-of-the-art works, namely, a) that they discover directions that are independent of the latent code, i.e., paths that are linear, and b) that their evaluation relies either on visual inspection or on laborious human labeling. More specifically, we propose to learn non-linear warpings on the latent space, each one parametrized by a set of RBF-based latent space warping functions, and where each warping gives rise to a family of non-linear paths via the gradient of the function. Building on the work of Voynov and Babenko, that discovers linear paths, we optimize the trainable parameters of the set of RBFs, so as that images that are generated by codes along different paths, are easily distinguishable by a discriminator network. This leads to easily distinguishable image transformations, such as pose and facial expressions in facial images. We show that linear paths can be derived as a special case of our method, and show experimentally that non-linear paths in the latent space lead to steeper, more disentangled and interpretable changes in the image space than in state-of-the art methods, both qualitatively and quantitatively. We make the code and the pretrained models publicly available at: this https URL.

Multimodal Earth observation data fusion: Graph-based approach in shared latent space

A framework for deriving a class of new global affine invariants for both object matching and positioning based on a novel concept of cross-weighted moments with fractional weights is presented. The fractional weight factor allows for a more flexible range to balance between the capability to discriminate between objects that differ only in small shape details and the sensitivity of small shape details to the presence of the noise. Moreover, it makes it possible to arrive at low order (zero order) affine invariants that are more robust than those derived from higher order regular moments. The affine transformation parameters are recovered from the zero and the first order cross-weighted moments without requiring any feature point correspondence information. The equations used to find the affine transformation parameters are linear algebraic. The sensitivity of the cross-weighted moment invariants to noise, missing data, and perspective effects is shown on real images.

Automatic animation synthesis has attracted much attention from the community. As most existing methods take a small number of discrete expressions rather than continuous expressions, their integrity and reality of the facial expressions is often compromised. In addition, the easy manipulation with simple inputs and unsupervised processing, although being important to the automatic facial expression animation applications, is relatively less concerned. To address these issues, we propose an unsupervised continuous automatic facial expression animation approach through action units (AU) transfer in the latent space of generative adversarial networks. The expression descriptor which is depicted with AU vector is transferred into the input image without the need of labeled pairs of images and even without their expressions and further network training. We also propose a new approach to quickly generate input image's latent code and cluster the boundaries of different AU attributes with their latent codes. Two latent code operators, vector addition and continuous interpolation, are leveraged for facial expression animation simulating align with the boundaries in the latent space. Experiments have shown that the proposed approach is effective on facial expression translation and animation synthesis.