Related papers: ContraCLIP: Interpretable GAN generation driven by…

Recent research has shown that it is possible to find interpretable directions in the latent spaces of pre-trained Generative Adversarial Networks (GANs). These directions enable controllable image generation and support a wide range of…

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,…

The semantically disentangled latent subspace in GAN provides rich interpretable controls in image generation. This paper includes two contributions on semantic latent subspace analysis in the scenario of face generation using StyleGAN2.…

Generative Adversarial Networks (GANs) are currently an indispensable tool for visual editing, being a standard component of image-to-image translation and image restoration pipelines. Furthermore, GANs are especially useful for…

This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging, lighting, and time of day. We identify important latent…

As recent generative models can generate photo-realistic images, people seek to understand the mechanism behind the generation process. Interpretable generation process is beneficial to various image editing applications. In this work, we…

This paper addresses the problem of finding interpretable directions in the latent space of pre-trained Generative Adversarial Networks (GANs) to facilitate controllable image synthesis. Such interpretable directions correspond to…

A large body of recent work has identified transformations in the latent spaces of generative adversarial networks (GANs) that consistently and interpretably transform generated images. But existing techniques for identifying these…

Generative models have been very popular in the recent years for their image generation capabilities. GAN-based models are highly regarded for their disentangled latent space, which is a key feature contributing to their success in…

Leveraging StyleGAN's expressivity and its disentangled latent codes, existing methods can achieve realistic editing of different visual attributes such as age and gender of facial images. An intriguing yet challenging problem arises: Can…

Generative adversarial nets (GANs) have been successfully applied in many fields like image generation, inpainting, super-resolution and drug discovery, etc., by now, the inner process of GANs is far from been understood. To get deeper…

Despite the recent advance of Generative Adversarial Networks (GANs) in high-fidelity image synthesis, there lacks enough understanding of how GANs are able to map a latent code sampled from a random distribution to a photo-realistic image.…

Generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) play an increasingly important role in medical image analysis. The latent spaces of these models often show semantically meaningful…

Generative Adversarial Networks (GANs) can synthesize realistic images, with the learned latent space shown to encode rich semantic information with various interpretable directions. However, due to the unstructured nature of the learned…

Recent advances in image generation have made diffusion models powerful tools for creating high-quality images. However, their iterative denoising process makes understanding and interpreting their semantic latent spaces more challenging…

In this work, we are dedicated to text-guided image generation and propose a novel framework, i.e., CLIP2GAN, by leveraging CLIP model and StyleGAN. The key idea of our CLIP2GAN is to bridge the output feature embedding space of CLIP and…

The latent spaces of GAN models often have semantically meaningful directions. Moving in these directions corresponds to human-interpretable image transformations, such as zooming or recoloring, enabling a more controllable generation…

We propose a novel method that trains a conditional Generative Adversarial Network (GAN) to generate visual interpretations of a Convolutional Neural Network (CNN). To comprehend a CNN, the GAN is trained with information on how the CNN…

This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and…

We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvement has been achieved, the quality of synthesized images is far from satisfactory due to three largely unresolved challenges. 1) The…