Related papers: Image Tokenizer Needs Post-Training

Poisson distribution is used for modeling noise in photon-limited imaging. While canonical examples include relatively exotic types of sensing like spectral imaging or astronomy, the problem is relevant to regular photography now more than…

Generative adversarial networks (GANs) have shown great success in applications such as image generation and inpainting. However, they typically require large datasets, which are often not available, especially in the context of prediction…

Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data. Despite the high-quality generated faces, some minority groups can be rarely generated from the trained models due…

The generator in the generative adversarial network (GAN) learns image generation in a coarse-to-fine manner in which earlier layers learn the overall structure of the image and the latter ones refine the details. To propagate the coarse…

Image cartoonization has attracted significant interest in the field of image generation. However, most of the existing image cartoonization techniques require re-training models using images of cartoon style. In this paper, we present…

Accurately controlling object count in text-to-image generation remains a key challenge. Supervised methods often fail, as training data rarely covers all count variations. Methods that manipulate the denoising process to add or remove…

Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each task, respectively. Existing approaches rely on spatial visual…

Image tokenizers play a central role in modern generative models, where the structure of the latent space critically determines the downstream generation performance. A key but underexplored property of effective latent representations is…

In recent years, Generative Adversarial Networks have become ubiquitous in both research and public perception, but how GANs convert an unstructured latent code to a high quality output is still an open question. In this work, we…

Dataset Condensation (DC) distills knowledge from large datasets into smaller ones, accelerating training and reducing storage requirements. However, despite notable progress, prior methods have largely overlooked the potential of…

Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the…

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…

In this work, we propose a modeling technique for jointly training image and video generation models by simultaneously learning to map latent variables with a fixed prior onto real images and interpolate over images to generate videos. The…

Deep neural networks provide state-of-the-art performance for image denoising, where the goal is to recover a near noise-free image from a noisy observation. The underlying principle is that neural networks trained on large datasets have…

We propose an approach to address two issues that commonly occur during training of unsupervised GANs. First, since GANs use only a continuous latent distribution to embed multiple classes or clusters of data, they often do not correctly…

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…

Advancements in language foundation models have primarily fueled the recent surge in artificial intelligence. In contrast, generative learning of non-textual modalities, especially videos, significantly trails behind language modeling. This…

Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts-such as entity missing, attribute binding errors, and incorrect relationships remains a…

As a class of generative artificial intelligence frameworks inspired by statistical physics, diffusion models have shown extraordinary performance in synthesizing complicated data distributions through a denoising process gradually guided…

The development of diffusion-based generative models over the past decade has largely proceeded independently of progress in representation learning. These diffusion models typically rely on regression-based objectives and generally lack…