Related papers: XQ-GAN: An Open-source Image Tokenization Framewor…

With the rise of large radio interferometric telescopes, particularly the SKA, there is a growing demand for computationally efficient image reconstruction techniques. Existing reconstruction methods, such as the CLEAN algorithm or proximal…

AutoRegressive Visual Generation (ARVG) models retain an architecture compatible with language models, while achieving performance comparable to diffusion-based models. Quantization is commonly employed in neural networks to reduce model…

Quantum generative modeling is among the promising candidates for achieving a practical advantage in data analysis. Nevertheless, one key challenge is to generate large-size images comparable to those generated by their classical…

In the realm of deep neural network deployment, low-bit quantization presents a promising avenue for enhancing computational efficiency. However, it often hinges on the availability of training data to mitigate quantization errors, a…

Masked transformer models for class-conditional image generation have become a compelling alternative to diffusion models. Typically comprising two stages - an initial VQGAN model for transitioning between latent space and image space, and…

Recent advances in visual generation have emphasized the importance of Latent Generative Models (LGMs), which critically depend on effective visual tokenizers to bridge pixels and semantic representations. However, tokenizers constructed on…

Vector quantized diffusion (VQ-Diffusion) is a powerful generative model for text-to-image synthesis, but sometimes can still generate low-quality samples or weakly correlated images with text input. We find these issues are mainly due to…

Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the…

The introduction of high-quality image generation models, particularly the StyleGAN family, provides a powerful tool to synthesize and manipulate images. However, existing models are built upon high-quality (HQ) data as desired outputs,…

Image reconstruction including image restoration and denoising is a challenging problem in the field of image computing. We present a new method, called X-GANs, for reconstruction of arbitrary corrupted resource based on a variant of…

This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. The…

Recent years have witnessed the dramatically increased interest in face generation with generative adversarial networks (GANs). A number of successful GAN algorithms have been developed to produce vivid face images towards different…

Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook.…

An ongoing trend in generative modelling research has been to push sample resolutions higher whilst simultaneously reducing computational requirements for training and sampling. We aim to push this trend further via the combination of…

Machine learning can be used as a systematic method to non-algorithmically program quantum computers. Quantum machine learning enables us to perform computations without breaking down an algorithm into its gate building blocks, eliminating…

Generative Adversarial Networks (GANs) coupled with self-supervised tasks have shown promising results in unconditional and semi-supervised image generation. We propose a self-supervised approach (LT-GAN) to improve the generation quality…

Effective image tokenization is crucial for both multi-modal understanding and generation tasks due to the necessity of the alignment with discrete text data. To this end, existing approaches utilize vector quantization (VQ) to project…

Recent work has shown the possibility of training generative models of 3D content from 2D image collections on small datasets corresponding to a single object class, such as human faces, animal faces, or cars. However, these models struggle…

Existing vector quantization (VQ) methods struggle with scalability, largely attributed to the instability of the codebook that undergoes partial updates during training. The codebook is prone to collapse as utilization decreases, due to…

The field of image generation is currently bifurcated into autoregressive (AR) models operating on discrete tokens and diffusion models utilizing continuous latents. This divide, rooted in the distinction between VQ-VAEs and VAEs, hinders…