Related papers: FICGen: Frequency-Inspired Contextual Disentanglem…

Latent Diffusion models (LDMs) have achieved remarkable results in synthesizing high-resolution images. However, the iterative sampling process is computationally intensive and leads to slow generation. Inspired by Consistency Models (song…

In this work, we present EchoGen, a unified framework for layout-to-image generation and image grounding, capable of generating images with accurate layouts and high fidelity to text descriptions (e.g., spatial relationships), while…

We explore different design choices for injecting noise into generative adversarial networks (GANs) with the goal of disentangling the latent space. Instead of traditional approaches, we propose feeding multiple noise codes through separate…

StyleGAN2 is a state-of-the-art network in generating realistic images. Besides, it was explicitly trained to have disentangled directions in latent space, which allows efficient image manipulation by varying latent factors. Editing…

In recent years, advancements in AIGC (Artificial Intelligence Generated Content) technology have significantly enhanced the capabilities of large text-to-image models. Despite these improvements, controllable image generation remains a…

Recent advancements in text-to-image diffusion models have yielded impressive results in generating realistic and diverse images. However, these models still struggle with complex prompts, such as those that involve numeracy and spatial…

Diffusion models are a powerful class of generative models capable of producing high-quality images from pure noise using a simple text prompt. While most methods which introduce additional spatial constraints into the generated images…

Text-to-image diffusion models often exhibit biases toward specific demographic groups, such as generating more males than females when prompted to generate images of engineers, raising ethical concerns and limiting their adoption. In this…

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…

In real-world images, slanted or curved texts, especially those on cans, banners, or badges, appear as frequently, if not more so, than flat texts due to artistic design or layout constraints. While high-quality visual text generation has…

In this work, we study the problem of Text-to-Image In-Context Learning (T2I-ICL). While Unified Multimodal LLMs (MLLMs) have advanced rapidly in recent years, they struggle with contextual reasoning in T2I-ICL scenarios. To address this…

In this paper, we present a novel paradigm to enhance the ability of object detector, e.g., expanding categories or improving detection performance, by training on synthetic dataset generated from diffusion models. Specifically, we…

Fine-grained object detection in challenging visual domains, such as vehicle damage assessment, presents a formidable challenge even for human experts to resolve reliably. While DiffusionDet has advanced the state-of-the-art through…

Diffusion models have exhibited substantial success in text-to-image generation. However, they often encounter challenges when dealing with complex and dense prompts involving multiple objects, attribute binding, and long descriptions. In…

Despite significant recent progress on generative models, controlled generation of images depicting multiple and complex object layouts is still a difficult problem. Among the core challenges are the diversity of appearance a given object…

Recent generative-prior-based methods have shown promising blind face restoration performance. They usually project the degraded images to the latent space and then decode high-quality faces either by single-stage latent optimization or…

Text-to-image (T2I) generation aims at producing realistic images corresponding to text descriptions. Generative Adversarial Network (GAN) has proven to be successful in this task. Typical T2I GANs are 2 phase methods that first pretrain an…

Generating controllable and physically plausible indoor scenes is a pivotal prerequisite for constructing high-fidelity simulation environments for embodied AI. However, existing deeplearning-based methods usually treat all objects as…

In recent years, considerable progress has been made in the visual quality of Generative Adversarial Networks (GANs). Even so, these networks still suffer from degradation in quality for high-frequency content, stemming from a spectrally…

Training GANs under limited data often leads to discriminator overfitting and memorization issues, causing divergent training. Existing approaches mitigate the overfitting by employing data augmentations, model regularization, or attention…