相关论文: FuseDream: Training-Free Text-to-Image Generation …

This paper introduces DeeCLIP, a novel framework for detecting AI-generated images using CLIP-ViT and fusion learning. Despite significant advancements in generative models capable of creating highly photorealistic images, existing…

Generating images with conditional descriptions gains increasing interests in recent years. However, existing conditional inputs are suffering from either unstructured forms (captions) or limited information and expensive labeling (scene…

Generative Artificial Intelligence (AI) has created unprecedented opportunities for creative expression, education, and research. Text-to-image systems such as DALL.E, Stable Diffusion, and Midjourney can now convert ideas into visuals…

In this research work we present CLIP-GLaSS, a novel zero-shot framework to generate an image (or a caption) corresponding to a given caption (or image). CLIP-GLaSS is based on the CLIP neural network, which, given an image and a…

With the widespread usage of VR devices and contents, demands for 3D scene generation techniques become more popular. Existing 3D scene generation models, however, limit the target scene to specific domain, primarily due to their training…

Drawing and annotating comic illustrations is a complex and difficult process. No existing machine learning algorithms have been developed to create comic illustrations based on descriptions of illustrations, or the dialogue in comics.…

In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generative models provide a consistent network architecture between…

Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but…

Text-image-to-video (TI2V) generation is a critical problem for controllable video generation using both semantic and visual conditions. Most existing methods typically add visual conditions to text-to-video (T2V) foundation models by…

Text-to-image synthesis models require the ability to generate diverse images while maintaining stability. To overcome this challenge, a number of methods have been proposed, including the collection of prompt-image datasets and the…

A comprehensive understanding of vision and language and their interrelation are crucial to realize the underlying similarities and differences between these modalities and to learn more generalized, meaningful representations. In recent…

Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little supervision. Generative Adversarial Networks (GANs) as an implicit…

Synthesizing high-quality photorealistic images with textual descriptions as a condition is very challenging. Generative Adversarial Networks (GANs), the classical model for this task, frequently suffer from low consistency between image…

Recent advancements in text-to-image generation have inspired researchers to generate datasets tailored for perception models using generative models, which prove particularly valuable in scenarios where real-world data is limited. In this…

Customizing pre-trained text-to-image generation model has attracted massive research interest recently, due to its huge potential in real-world applications. Although existing methods are able to generate creative content for a novel…

The rapid progress of generative models, such as GANs and diffusion models, has facilitated the creation of highly realistic images, raising growing concerns over their misuse in security-sensitive domains. While existing detectors perform…

Image tokenization, the process of transforming raw image pixels into a compact low-dimensional latent representation, has proven crucial for scalable and efficient image generation. However, mainstream image tokenization methods generally…

Due to the outstanding capability for data generation, Generative Adversarial Networks (GANs) have attracted considerable attention in unsupervised learning. However, training GANs is difficult, since the training distribution is dynamic…

In this paper, we present VideoGen, a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion. We leverage an…

Recent text-to-image diffusion models are able to generate convincing results of unprecedented quality. However, it is nearly impossible to control the shapes of different regions/objects or their layout in a fine-grained fashion. Previous…