English
Related papers

Related papers: CODA: Repurposing Continuous VAEs for Discrete Tok…

200 papers

The performance of Latent Diffusion Models (LDMs) is critically dependent on the quality of their visual tokenizers. While recent works have explored incorporating Vision Foundation Models (VFMs) into the tokenizers training via…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Tianci Bi , Xiaoyi Zhang , Yan Lu , Nanning Zheng

To enhance the interpretability of multimodal unified representations, many studies have focused on discrete unified representations. These efforts typically start with contrastive learning and gradually extend to the disentanglement of…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Hai Huang , Yan Xia , Shengpeng Ji , Shulei Wang , Hanting Wang , Minghui Fang , Jieming Zhu , Zhenhua Dong , Sashuai Zhou , Zhou Zhao

Recent advances in large language models (LLMs) have spurred interests in encoding images as discrete tokens and leveraging autoregressive (AR) frameworks for visual generation. However, the quantization process in AR-based visual…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Peng Zheng , Junke Wang , Yi Chang , Yizhou Yu , Rui Ma , Zuxuan Wu

Video face restoration faces a critical challenge in maintaining temporal consistency while recovering fine facial details from degraded inputs. This paper presents a novel approach that extends Vector-Quantized Variational Autoencoders…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Yan Chen , Hanlin Shang , Ce Liu , Yuxuan Chen , Hui Li , Weihao Yuan , Hao Zhu , Zilong Dong , Siyu Zhu

The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patterns caused by both…

Computer Vision and Pattern Recognition · Computer Science 2024-02-05 Zifan Yu , Erfan Bank Tavakoli , Meida Chen , Suya You , Raghuveer Rao , Sanjeev Agarwal , Fengbo Ren

Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental models that compress continuous visual data into discrete tokens. Existing methods have tried to improve the quantization strategy for better reconstruction quality,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Mingkai Jia , Wei Yin , Xiaotao Hu , Jiaxin Guo , Xiaoyang Guo , Qian Zhang , Xiao-Xiao Long , Ping Tan

In quantised autoencoders, images are usually split into local patches, each encoded by one token. This representation is redundant in the sense that the same number of tokens is spend per region, regardless of the visual information…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Tim Elsner , Paula Usinger , Victor Czech , Gregor Kobsik , Yanjiang He , Isaak Lim , Leif Kobbelt

Latent generative models have shown remarkable progress in high-fidelity image synthesis, typically using a two-stage training process that involves compressing images into latent embeddings via learned tokenizers in the first stage. The…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Tejaswini Medi , Hsien-Yi Wang , Arianna Rampini , Margret Keuper

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

Vector-quantized variational autoencoders (VQ-VAEs) are discrete autoencoders that compress images into discrete tokens. However, they are difficult to train due to discretization. In this paper, we propose a simple yet effective technique…

Machine Learning · Computer Science 2026-05-27 Tongda Xu , Wendi Zheng , Jiajun He , Jose Miguel Hernandez-Lobato , Yan Wang , Ya-Qin Zhang , Jie Tang

Most existing image tokenizers encode images into a fixed number of tokens or patches, overlooking the inherent variability in image complexity. To address this, we introduce Content-Adaptive Tokenizer (CAT), which dynamically adjusts…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Junhong Shen , Kushal Tirumala , Michihiro Yasunaga , Ishan Misra , Luke Zettlemoyer , Lili Yu , Chunting Zhou

Modern on-device neural network applications must operate under resource constraints while adapting to unpredictable domain shifts. However, this combined challenge-model compression and domain adaptation-remains largely unaddressed, as…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Yoojin Kwon , Hongjun Suh , Wooseok Lee , Taesik Gong , Songyi Han , Hyung-Sin Kim

Video large language models have demonstrated remarkable capabilities in video understanding tasks. However, the redundancy of video tokens introduces significant computational overhead during inference, limiting their practical deployment.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Yinchao Ma , Qiang Zhou , Zhibin Wang , Xianing Chen , Hanqing Yang , Jun Song , Bo Zheng

Deep learning models for image compression often face practical limitations in hardware-constrained applications. Although these models achieve high-quality reconstructions, they are typically complex, heavyweight, and require substantial…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Caroline Mazini Rodrigues , Nicolas Keriven , Thomas Maugey

Constructing a compressed latent space through a variational autoencoder (VAE) is the key for efficient 3D diffusion models. This paper introduces COD-VAE that encodes 3D shapes into a COmpact set of 1D latent vectors without sacrificing…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 In Cho , Youngbeom Yoo , Subin Jeon , Seon Joo Kim

Video captioning is a challenging task that captures different visual parts and describes them in sentences, for it requires visual and linguistic coherence. The attention mechanism in the current video captioning method learns to assign…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Zhixin Sun , Xian Zhong , Shuqin Chen , Lin Li , Luo Zhong

Visual tokenizers map high-dimensional raw pixels into a compressed representation for downstream modeling. Beyond compression, tokenizers dictate what information is preserved and how it is organized. A de facto standard approach to video…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Andrei Atanov , Jesse Allardice , Roman Bachmann , Oğuzhan Fatih Kar , R Devon Hjelm , David Griffiths , Peter Fu , Afshin Dehghan , Amir Zamir

Visual autoregressive (AR) generation offers a promising path toward unifying vision and language models, yet its performance remains suboptimal against diffusion models. Prior work often attributes this gap to tokenizer limitations and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Qiyuan He , Yicong Li , Haotian Ye , Jinghao Wang , Xinyao Liao , Pheng-Ann Heng , Stefano Ermon , James Zou , Angela Yao

Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks, e.g., image generation and visual question answering. The…

Computer Vision and Pattern Recognition · Computer Science 2025-05-16 Wenxuan Wang , Fan Zhang , Yufeng Cui , Haiwen Diao , Zhuoyan Luo , Huchuan Lu , Jing Liu , Xinlong Wang

In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE) from scratch, which primarily emphasizes low-level details,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Bowei Chen , Sai Bi , Hao Tan , He Zhang , Tianyuan Zhang , Zhengqi Li , Yuanjun Xiong , Jianming Zhang , Kai Zhang