Related papers: MaskBit: Embedding-free Image Generation via Bit T…

Text-to-image generation is a significant domain in modern computer vision and has achieved substantial improvements through the evolution of generative architectures. Among these, there are diffusion-based models that have demonstrated…

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…

We present Bit Diffusion: a simple and generic approach for generating discrete data with continuous state and continuous time diffusion models. The main idea behind our approach is to first represent the discrete data as binary bits, and…

This paper presents SimMIM, a simple framework for masked image modeling. We simplify recently proposed related approaches without special designs such as block-wise masking and tokenization via discrete VAE or clustering. To study what let…

Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images…

Training computer-vision related algorithms on medical images for disease diagnosis or image segmentation is difficult due to the lack of training data, labeled samples, and privacy concerns. For this reason, a robust generative method to…

Advances in the realm of Generative Adversarial Networks (GANs) have led to architectures capable of producing amazingly realistic images such as StyleGAN2, which, when trained on the FFHQ dataset, generates images of human faces from…

The absence of large-scale masked face datasets challenges masked face detection and recognition. We propose a two-step generative data augmentation framework combining rule-based mask warping with unpaired image-to-image translation via…

Current state-of-the-art photorealistic generators are computationally expensive, involve unstable training processes, and have real and synthetic distributions that are dissimilar in higher-dimensional spaces. To solve these issues, we…

Vision Transformer models process input images by dividing them into a spatially regular grid of equal-size patches. Conversely, Transformers were originally introduced over natural language sequences, where each token represents a subword…

In recent years, with the realistic generation results and a wide range of personalized applications, diffusion-based generative models gain huge attention in both visual and audio generation areas. Compared to the considerable advancements…

Masked (or absorbing) diffusion is actively explored as an alternative to autoregressive models for generative modeling of discrete data. However, existing work in this area has been hindered by unnecessarily complex model formulations and…

Acceleration methods for diffusion models (e.g., token merging or downsampling) typically optimize synthesis quality under reduced compute, yet often ignore discriminative capacity. We revisit token compression with a joint objective and…

We introduce FewGAN, a generative model for generating novel, high-quality and diverse images whose patch distribution lies in the joint patch distribution of a small number of N>1 training samples. The method is, in essence, a hierarchical…

Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion…

Transformers are the backbone of powerful foundation models for many Vision and Natural Language Processing tasks. But their compute and memory/storage footprint is large, and so, serving such models is expensive often requiring high-end…

We present a novel algorithm to reduce tensor compute required by a conditional image generation autoencoder without sacrificing quality of photo-realistic image generation. Our method is device agnostic, and can optimize an autoencoder for…

Recent advances in visually-induced audio generation are based on sampling short, low-fidelity, and one-class sounds. Moreover, sampling 1 second of audio from the state-of-the-art model takes minutes on a high-end GPU. In this work, we…

Large-scale text-to-image diffusion models have made amazing advances. However, the status quo is to use text input alone, which can impede controllability. In this work, we propose GLIGEN, Grounded-Language-to-Image Generation, a novel…

Image inpainting, which refers to the synthesis of missing regions in an image, can help restore occluded or degraded areas and also serve as a precursor task for self-supervision. The current state-of-the-art models for image inpainting…