Related papers: Discovering Multiple and Diverse Directions for Co…

An important line of research attempts to explain CNN image classifier predictions and intermediate layer representations in terms of human-understandable concepts. Previous work supports that deep representations are linearly separable…

Although manipulating facial attributes by Generative Adversarial Networks (GANs) has been remarkably successful recently, there are still some challenges in explicit control of features such as pose, expression, lighting, etc. Recent…

State-of-the-art generative models (e.g. StyleGAN3 \cite{karras2021alias}) often generate photorealistic images based on vectors sampled from their latent space. However, the ability to control the output is limited. Here we present our…

The success of deep neural nets heavily relies on their ability to encode complex relations between their input and their output. While this property serves to fit the training data well, it also obscures the mechanism that drives…

StyleGAN has demonstrated the ability of GANs to synthesize highly-realistic faces of imaginary people from random noise. One limitation of GAN-based image generation is the difficulty of controlling the features of the generated image, due…

Semantic image synthesis is a process for generating photorealistic images from a single semantic mask. To enrich the diversity of multimodal image synthesis, previous methods have controlled the global appearance of an output image by…

In the context of MDPs with high-dimensional states, downstream tasks are predominantly applied on a compressed, low-dimensional representation of the original input space. A variety of learning objectives have therefore been used to attain…

Recent studies have shown how disentangling images into content and feature spaces can provide controllable image translation/ manipulation. In this paper, we propose a framework to enable utilizing discrete multi-labels to control which…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Gradient-based attention modeling has been used widely as a way to visualize and understand convolutional neural networks. However, exploiting these visual explanations during the training of generative adversarial networks (GANs) is an…

Empirical evidence shows that deep vision networks often represent concepts as directions in latent space with concept information written along directional components in the vector representation of the input. However, the mechanism to…

High quality facial image editing is a challenging problem in the movie post-production industry, requiring a high degree of control and identity preservation. Previous works that attempt to tackle this problem may suffer from the…

Learning useful representations of complex data has been the subject of extensive research for many years. With the diffusion of Deep Neural Networks, Variational Autoencoders have gained lots of attention since they provide an explicit…

Generative adversarial networks (GANs) have many application areas including image editing, domain translation, missing data imputation, and support for creative work. However, GANs are considered 'black boxes'. Specifically, the end-users…

Face attribute editing aims to generate faces with one or multiple desired face attributes manipulated while other details are preserved. Unlike prior works such as GAN inversion, which has an expensive reverse mapping process, we propose a…

Learning-based gaze estimation methods require large amounts of training data with accurate gaze annotations. Facing such demanding requirements of gaze data collection and annotation, several image synthesis methods were proposed, which…

Millions of images of human faces are captured every single day; but these photographs portray the likeness of an individual with a fixed pose, expression, and appearance. Portrait image animation enables the post-capture adjustment of…

Despite the success of Generative Adversarial Networks (GANs) in image synthesis, applying trained GAN models to real image processing remains challenging. Previous methods typically invert a target image back to the latent space either by…

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.).…

Many recent works have been proposed for face image editing by leveraging the latent space of pretrained GANs. However, few attempts have been made to directly apply them to videos, because 1) they do not guarantee temporal consistency, 2)…