Related papers: 3D representation in 512-Byte:Variational tokenize…

Learned progressive image compression is gaining momentum as it allows improved image reconstruction as more bits are decoded at the receiver. We propose a progressive image compression method in which an image is first represented as a…

This paper introduces Associative Compression Networks (ACNs), a new framework for variational autoencoding with neural networks. The system differs from existing variational autoencoders (VAEs) in that the prior distribution used to model…

Generative models able to synthesize layouts of different kinds (e.g. documents, user interfaces or furniture arrangements) are a useful tool to aid design processes and as a first step in the generation of synthetic data, among other…

Vector-Quantized (VQ-based) generative models usually consist of two basic components, i.e., VQ tokenizers and generative transformers. Prior research focuses on improving the reconstruction fidelity of VQ tokenizers but rarely examines how…

Convolutional neural networks (CNN) have demonstrated outstanding Compressed Sensing (CS) performance compared to traditional, hand-crafted methods. However, they are broadly limited in terms of generalisability, inductive bias and…

Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem. The problem is particularly acute when control over identity features is required. In this…

Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data representations for large language models, diffusion models, and…

Feed-forward 3D reconstruction models based on Vision Transformers can directly estimate scene geometry and camera poses from a small set of input images, but scaling them to video inputs with hundreds or thousands of frames remains…

The exponential growth of video traffic has placed increasing demands on bandwidth and storage infrastructure, particularly for content delivery networks (CDNs) and edge devices. While traditional video codecs like H.264 and HEVC achieve…

Visual Autoregressive (VAR) models enable efficient image generation via next-scale prediction but face escalating computational costs as sequence length grows. Existing static pruning methods degrade performance by permanently removing…

We propose a novel algorithm for quantizing continuous latent representations in trained models. Our approach applies to deep probabilistic models, such as variational autoencoders (VAEs), and enables both data and model compression. Unlike…

Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attention mechanisms poses significant challenges, often leading to…

Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However, they produce blurry images due to a lack of explicit…

For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents an image as a sequence of discrete codes. A short sequence length is important for an AR model to reduce its computational costs to consider…

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…

Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding tasks. However, the increasing demand for high-resolution image and long-video understanding results in substantial token counts,…

We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel…

Visual autoregressive modeling (VAR) via next-scale prediction has emerged as a scalable image generation paradigm. While Key and Value (KV) caching in large language models (LLMs) has been extensively studied, next-scale prediction…

Transformer-based methods have demonstrated strong potential in hyperspectral pansharpening by modeling long-range dependencies. However, their effectiveness is often limited by redundant token representations and a lack of multi-scale…

Recent advances in sparse voxel representations have significantly improved the quality of 3D content generation, enabling high-resolution modeling with fine-grained geometry. However, existing frameworks suffer from severe computational…