English
Related papers

Related papers: VAR-3D: View-aware Auto-Regressive Model for Text-…

200 papers

Visual Autoregressive (VAR) models have emerged as a powerful paradigm for image synthesis by performing hierarchical next-scale prediction. However, VAR models are inherently prone to cascading error propagation, where subtle coarse-scale…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Ligong Bi , Tao Huang , Jianyuan Guo , Chang Xu

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…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Qihang Yu , Ju He , Xueqing Deng , Xiaohui Shen , Liang-Chieh Chen

Visual Autoregressive (VAR) modeling inefficiently applies a fixed computational depth to each position when generating high-resolution images. While existing methods accelerate inference by pruning tokens using frequency maps, their binary…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Chunliang Li , Tianze Cao , Sanyuan Zhao

Recent advances in subject-driven image generation using diffusion models have attracted considerable attention for their remarkable capabilities in producing high-quality images. Nevertheless, the potential of Visual Autoregressive (VAR)…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Xin Jiang , Jingwen Chen , Yehao Li , Yingwei Pan , Kezhou Chen , Zechao Li , Ting Yao , Tao Mei

Vector-quantized representations enable powerful discrete generative models but lack semantic structure in token space, limiting interpretable human control. We introduce SOM-VQ, a tokenization method that combines vector quantization with…

Machine Learning · Computer Science 2026-02-25 Alessandro Londei , Denise Lanzieri , Matteo Benati

Conventional wisdom suggests that autoregressive models are used to process discrete data. When applied to continuous modalities such as visual data, Visual AutoRegressive modeling (VAR) typically resorts to quantization-based approaches to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Chenze Shao , Fandong Meng , Jie Zhou

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…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Zecheng Tang , Jiaye Fu , Qiankun Gao , Haijie Li , Yanmin Wu , Jiaqi Zhang , Siwei Ma , Jian Zhang

In this paper we demonstrate methods for reliable and efficient training of discrete representation using Vector-Quantized Variational Auto-Encoder models (VQ-VAEs). Discrete latent variable models have been shown to learn nontrivial…

Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs). Nonetheless, existing Text-to-3D approaches often grapple with challenges such as…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Yiwen Chen , Chi Zhang , Xiaofeng Yang , Zhongang Cai , Gang Yu , Lei Yang , Guosheng Lin

Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in discrete latent spaces to align with the tokens from large…

Computer Vision and Pattern Recognition · Computer Science 2025-10-09 Ziyuan Huang , DanDan Zheng , Cheng Zou , Rui Liu , Xiaolong Wang , Kaixiang Ji , Weilong Chai , Jianxin Sun , Libin Wang , Yongjie Lv , Taozhi Huang , Jiajia Liu , Qingpei Guo , Ming Yang , Jingdong Chen , Jun Zhou

Variational autoencoders (VAEs) have received much attention recently as an end-to-end architecture for text generation with latent variables. In this paper, we investigate several multi-level structures to learn a VAE model to generate…

Computation and Language · Computer Science 2019-06-21 Dinghan Shen , Asli Celikyilmaz , Yizhe Zhang , Liqun Chen , Xin Wang , Jianfeng Gao , Lawrence Carin

Vector-Quantized Variational Autoencoders (VQ-VAE)[1] provide an unsupervised model for learning discrete representations by combining vector quantization and autoencoders. In this paper, we study the use of VQ-VAE for representation…

Image and Video Processing · Electrical Eng. & Systems 2019-03-05 Hanwei Wu , Markus Flierl

Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to…

Computer Vision and Pattern Recognition · Computer Science 2021-11-08 Ming Ding , Zhuoyi Yang , Wenyi Hong , Wendi Zheng , Chang Zhou , Da Yin , Junyang Lin , Xu Zou , Zhou Shao , Hongxia Yang , Jie Tang

The emergence of visual autoregressive (AR) models has revolutionized image generation while presenting new challenges for synthetic image detection. Unlike previous GAN or diffusion-based methods, AR models generate images through discrete…

Computer Vision and Pattern Recognition · Computer Science 2025-10-08 Yanran Zhang , Bingyao Yu , Yu Zheng , Wenzhao Zheng , Yueqi Duan , Lei Chen , Jie Zhou , Jiwen Lu

Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular…

Machine Learning · Statistics 2017-03-07 Matt J. Kusner , Brooks Paige , José Miguel Hernández-Lobato

Generating multi-view images from human instructions is crucial for 3D content creation. The primary challenges involve maintaining consistency across multiple views and effectively synthesizing shapes and textures under diverse conditions.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 JiaKui Hu , Yuxiao Yang , Jialun Liu , Jinbo Wu , Chen Zhao , Yanye Lu

Text-to-3D generation approaches have advanced significantly by leveraging pretrained 2D diffusion priors, producing high-quality and 3D-consistent outputs. However, they often fail to produce out-of-domain (OOD) or rare concepts, yielding…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Yosef Dayani , Omer Benishu , Sagie Benaim

Vector Quantized Variational AutoEncoders (VQ-VAEs) are designed to compress a continuous input to a discrete latent space and reconstruct it with minimal distortion. They operate by maintaining a set of vectors -- often referred to as the…

As Vision-Language Models (VLMs) become increasingly sophisticated and widely used, it becomes more and more crucial to understand their decision-making process. Traditional explainability methods, designed for classification tasks,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Walid Bousselham , Angie Boggust , Hendrik Strobelt , Hilde Kuehne

Variational autoencoders (VAEs) are fundamental for generative modeling and image reconstruction, yet their performance often struggles to maintain high fidelity in reconstructions. This study introduces a hybrid model, quantum variational…

Computer Vision and Pattern Recognition · Computer Science 2025-03-10 Farina Riaz , Fakhar Zaman , Hajime Suzuki , Sharif Abuadbba , David Nguyen