Related papers: StyleGAN knows Normal, Depth, Albedo, and More

Neural rendering techniques promise efficient photo-realistic image synthesis while at the same time providing rich control over scene parameters by learning the physical image formation process. While several supervised methods have been…

Text-to-image synthesis has recently seen significant progress thanks to large pretrained language models, large-scale training data, and the introduction of scalable model families such as diffusion and autoregressive models. However, the…

We propose a framework for the automatic one-shot segmentation of synthetic images generated by a StyleGAN. Our framework is based on the observation that the multi-scale hidden features in the GAN generator hold useful semantic information…

Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning…

Deep learning has brought an unprecedented progress in computer vision and significant advances have been made in predicting subjective properties inherent to visual data (e.g., memorability, aesthetic quality, evoked emotions, etc.).…

In the majority of GAN architectures, the latent space is defined as a set of vectors of given dimensionality. Such representations are not easily interpretable and do not capture spatial information of image content directly. In this work,…

Reconstruction of human clothing is an important task and often relies on intrinsic image decomposition. With a lack of domain-specific data and coarse evaluation metrics, existing models failed to produce satisfying results for graphics…

Unconditional human image generation is an important task in vision and graphics, which enables various applications in the creative industry. Existing studies in this field mainly focus on "network engineering" such as designing new…

Generative Adversarial Networks have been crucial in the developments made in unsupervised learning in recent times. Exemplars of image synthesis from text or other images, these networks have shown remarkable improvements over conventional…

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…

Photo-realistic re-rendering of a human from a single image with explicit control over body pose, shape and appearance enables a wide range of applications, such as human appearance transfer, virtual try-on, motion imitation, and novel view…

Automatically generating maps from satellite images is an important task. There is a body of literature which tries to address this challenge. We created a more expansive survey of the task by experimenting with different models and adding…

Generative adversarial networks (GANs) synthesize realistic images from random latent vectors. Although manipulating the latent vectors controls the synthesized outputs, editing real images with GANs suffers from i) time-consuming…

Recent research has shown that controllable image generation based on pre-trained GANs can benefit a wide range of computer vision tasks. However, less attention has been devoted to 3D vision tasks. In light of this, we propose a novel…

This paper investigates an open research task of text-to-image synthesis for automatically generating or manipulating images from text descriptions. Prevailing methods mainly use the text as conditions for GAN generation, and train…

The disentanglement of StyleGAN latent space has paved the way for realistic and controllable image editing, but does StyleGAN know anything about temporal motion, as it was only trained on static images? To study the motion features in the…

Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representations of the data in…

Image steganography is a procedure for hiding messages inside pictures. While other techniques such as cryptography aim to prevent adversaries from reading the secret message, steganography aims to hide the presence of the message itself.…

In general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in…

Generative Adversarial Networks (GANs) have recently advanced image synthesis by learning the underlying distribution of the observed data. However, how the features learned from solving the task of image generation are applicable to other…