Related papers: MoVQ: Modulating Quantized Vectors for High-Fideli…

Unconditional video generation is a challenging task that involves synthesizing high-quality videos that are both coherent and of extended duration. To address this challenge, researchers have used pretrained StyleGAN image generators for…

Although autoregressive models have achieved promising results on image generation, their unidirectional generation process prevents the resultant images from fully reflecting global contexts. To address the issue, we propose an effective…

We present a new perspective of achieving image synthesis by viewing this task as a visual token generation problem. Different from existing paradigms that directly synthesize a full image from a single input (e.g., a latent code), the new…

The current conditional autoregressive image generation methods have shown promising results, yet their potential remains largely unexplored in the practical unsupervised image translation domain, which operates without explicit…

The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model…

Recent progress in generative compression technology has significantly improved the perceptual quality of compressed data. However, these advancements primarily focus on producing high-frequency details, often overlooking the ability of…

Rich feature representations derived from CLIP-ViT have been widely utilized in AI-generated image detection. While most existing methods primarily leverage features from the final layer, we systematically analyze the contributions of…

In this work, we present a novel direction to build an image tokenizer directly on top of a frozen vision foundation model, which is a largely underexplored area. Specifically, we employ a frozen vision foundation model as the encoder of…

We introduce a simple but effective unsupervised method for generating realistic and diverse images. We train a class-conditional GAN model without using manually annotated class labels. Instead, our model is conditional on labels…

Post-training quantization (PTQ) efficiently compresses vision models, but unfortunately, it accompanies a certain degree of accuracy degradation. Reconstruction methods aim to enhance model performance by narrowing the gap between the…

Time series generation (TSG) studies have mainly focused on the use of Generative Adversarial Networks (GANs) combined with recurrent neural network (RNN) variants. However, the fundamental limitations and challenges of training GANs still…

How can we accurately quantize a pre-trained Vision Transformer model? Quantization algorithms compress Vision Transformers (ViTs) into low-bit formats, reducing memory and computation demands with minimal accuracy degradation. However,…

Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval between discrete values). Unlike prior arts that carefully tune…

In quantum many-body systems, measurements can induce qualitative new features, but their simulation is hindered by the exponential complexity involved in sampling the measurement results. We propose to use machine learning to assist the…

Machine learning-assisted diagnosis shows promise, yet medical imaging datasets are often scarce, imbalanced, and constrained by privacy, making data augmentation essential. Classical generative models typically demand extensive…

We investigate how to generate multimodal image outputs, such as RGB, depth, and surface normals, with a single generative model. The challenge is to produce outputs that are realistic, and also consistent with each other. Our solution…

PICNet pioneered the generation of multiple and diverse results for image completion task, but it required a careful balance between $\mathcal{KL}$ loss (diversity) and reconstruction loss (quality), resulting in a limited diversity and…

By optimizing the rate-distortion-realism trade-off, generative compression approaches produce detailed, realistic images, even at low bit rates, instead of the blurry reconstructions produced by rate-distortion optimized models. However,…

Leveraging pre-trained visual language models has become a widely adopted approach for improving performance in downstream visual question answering (VQA) applications. However, in the specialized field of medical VQA, the scarcity of…

Diffusion models (DMs) generate remarkable high quality images via the stochastic denoising process, which unfortunately incurs high sampling time. Post-quantizing the trained diffusion models in fixed bit-widths, e.g., 4 bits on weights…