Related papers: Learning Input-agnostic Manipulation Directions in…
The goal of our paper is to semantically edit parts of an image matching a given text that describes desired attributes (e.g., texture, colour, and background), while preserving other contents that are irrelevant to the text. To achieve…
While diffusion models have significantly advanced the quality of image generation their capability to accurately and coherently render text within these images remains a substantial challenge. Conventional diffusion-based methods for scene…
Despite significant advancements in image customization with diffusion models, current methods still have several limitations: 1) unintended changes in non-target areas when regenerating the entire image; 2) guidance solely by a reference…
Unconstrained Image generation with high realism is now possible using recent Generative Adversarial Networks (GANs). However, it is quite challenging to generate images with a given set of attributes. Recent methods use style-based GAN…
This work integrates StyleGAN, DragGAN and Principal Component Analysis (PCA) to enhance the latent space efficiency and controllability of GAN-generated images. Style-GAN provides a structured latent space, DragGAN enables intuitive image…
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.…
Despite recent advances, diffusion-based text-to-image models still struggle with accurate text rendering. Several studies have proposed fine-tuning or training-free refinement methods for accurate text rendering. However, the critical…
Recent advances in diffusion models enable many powerful instruments for image editing. One of these instruments is text-driven image manipulations: editing semantic attributes of an image according to the provided text description. %…
In subject-driven text-to-image synthesis, the synthesis process tends to be heavily influenced by the reference images provided by users, often overlooking crucial attributes detailed in the text prompt. In this work, we propose…
Research in vision-language models has seen rapid developments off-late, enabling natural language-based interfaces for image generation and manipulation. Many existing text guided manipulation techniques are restricted to specific classes…
Learning continuous representations from unlabeled textual data has been increasingly studied for benefiting semi-supervised learning. Although it is relatively easier to interpret discrete representations, due to the difficulty of…
The success of Deep Generative Models at high-resolution image generation has led to their extensive utilization for style editing of real images. Most existing methods work on the principle of inverting real images onto their latent space,…
Text-driven style transfer aims to merge the style of a reference image with content described by a text prompt. Recent advancements in text-to-image models have improved the nuance of style transformations, yet significant challenges…
Diffusion models have demonstrated high-quality performance in conditional text-to-image generation, particularly with structural cues such as edges, layouts, and depth. However, lighting conditions have received limited attention and…
In this paper, we perform an in-depth study of the properties and applications of aligned generative models. We refer to two models as aligned if they share the same architecture, and one of them (the child) is obtained from the other (the…
The ability of Generative Adversarial Networks to encode rich semantics within their latent space has been widely adopted for facial image editing. However, replicating their success with videos has proven challenging. Sets of high-quality…
Despite the burst of innovative methods for controlling the diffusion process, effectively controlling image styles in text-to-image generation remains a challenging task. Many adapter-based methods impose image representation conditions on…
StyleGAN is arguably one of the most intriguing and well-studied generative models, demonstrating impressive performance in image generation, inversion, and manipulation. In this work, we explore the recent StyleGAN3 architecture, compare…
Learning interpretable and interpolatable latent representations has been an emerging research direction, allowing researchers to understand and utilize the derived latent space for further applications such as visual synthesis or…
Semantic facial attribute editing using pre-trained Generative Adversarial Networks (GANs) has attracted a great deal of attention and effort from researchers in recent years. Due to the high quality of face images generated by StyleGANs,…