Related papers: Stabilize the Latent Space for Image Autoregressiv…
Instead of performing text-conditioned denoising in the image domain, latent diffusion models (LDMs) operate in latent space of a variational autoencoder (VAE), enabling more efficient processing at reduced computational costs. However,…
In this study, we focus on sampling from the latent space of generative models built upon autoencoders so as the reconstructed samples are lifelike images. To do to, we introduce a novel post-training sampling algorithm rooted in the…
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…
Autoregressive modeling has been a huge success in the field of natural language processing (NLP). Recently, autoregressive models have emerged as a significant area of focus in computer vision, where they excel in producing high-quality…
The development of autoregressive modeling (AM) in computer vision lags behind natural language processing (NLP) in self-supervised pre-training. This is mainly caused by the challenge that images are not sequential signals and lack a…
Generative 3D Painting is among the top productivity boosters in high-resolution 3D asset management and recycling. Ever since text-to-image models became accessible for inference on consumer hardware, the performance of 3D Painting methods…
Neuroimaging data, particularly from techniques like MRI or PET, offer rich but complex information about brain structure and activity. To manage this complexity, latent representation models - such as Autoencoders, Generative Adversarial…
Image-based generative methods, such as generative adversarial networks (GANs) have already been able to generate realistic images with much context control, specially when they are conditioned. However, most successful frameworks share a…
Diffusion models (DMs) have achieved state-of-the-art results for image synthesis tasks as well as density estimation. Applied in the latent space of a powerful pretrained autoencoder (LDM), their immense computational requirements can be…
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…
Pixel diffusion models have recently regained attention for visual generation. However, training advanced pixel-space models from scratch demands prohibitive computational and data resources. To address this, we propose the Latent-to-Pixel…
Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notable redundancy in their computation: when sampling discrete…
Generative Adversarial Networks (GAN) is currently widely used as an unsupervised image generation method. Current state-of-the-art GANs can generate photorealistic images with high resolution. However, a large amount of data is required,…
In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for visual generation via next-token prediction. While scaling…
Image tokenization has significantly advanced visual generation and multimodal modeling, particularly when paired with autoregressive models. However, current methods face challenges in balancing efficiency and fidelity: high-resolution…
Generative modeling frameworks have emerged as an effective approach to capture high-dimensional image distributions from large datasets without requiring domain-specific knowledge, a capability essential for longitudinal disease…
Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying…
This paper challenges the dominance of continuous pipelines in visual generation. We systematically investigate the performance gap between discrete and continuous methods. Contrary to the belief that discrete tokenizers are intrinsically…
Lossless image compression is an essential research field in image compression. Recently, learning-based image compression methods achieved impressive performance compared with traditional lossless methods, such as WebP, JPEG2000, and FLIF.…
Modeling the time-dependent evolution of electron density is essential for understanding quantum mechanical behaviors of condensed matter and enabling predictive simulations in spectroscopy, photochemistry, and ultrafast science. Yet, while…