Hita: Holistic Tokenizer for Autoregressive Image Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zheng, Anlin, Wang, Haochen, Zhao, Yucheng, Deng, Weipeng, Wang, Tiancai, Zhang, Xiangyu, Qi, Xiaojuan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918088765603840
author Zheng, Anlin
Wang, Haochen
Zhao, Yucheng
Deng, Weipeng
Wang, Tiancai
Zhang, Xiangyu
Qi, Xiaojuan
author_facet Zheng, Anlin
Wang, Haochen
Zhao, Yucheng
Deng, Weipeng
Wang, Tiancai
Zhang, Xiangyu
Qi, Xiaojuan
contents Vanilla autoregressive image generation models generate visual tokens step-by-step, limiting their ability to capture holistic relationships among token sequences. Moreover, because most visual tokenizers map local image patches into latent tokens, global information is limited. To address this, we introduce \textit{Hita}, a novel image tokenizer for autoregressive (AR) image generation. It introduces a holistic-to-local tokenization scheme with learnable holistic queries and local patch tokens. Hita incorporates two key strategies to better align with the AR generation process: 1) {arranging} a sequential structure with holistic tokens at the beginning, followed by patch-level tokens, and using causal attention to maintain awareness of previous tokens; and 2) adopting a lightweight fusion module before feeding the de-quantized tokens into the decoder to control information flow and prioritize holistic tokens. Extensive experiments show that Hita accelerates the training speed of AR generators and outperforms those trained with vanilla tokenizers, achieving \textbf{2.59 FID} and \textbf{281.9 IS} on the ImageNet benchmark. Detailed analysis of the holistic representation highlights its ability to capture global image properties, such as textures, materials, and shapes. Additionally, Hita also demonstrates effectiveness in zero-shot style transfer and image in-painting. The code is available at \href{https://github.com/CVMI-Lab/Hita}{https://github.com/CVMI-Lab/Hita}.
format Preprint
id arxiv_https___arxiv_org_abs_2507_02358
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hita: Holistic Tokenizer for Autoregressive Image Generation
Zheng, Anlin
Wang, Haochen
Zhao, Yucheng
Deng, Weipeng
Wang, Tiancai
Zhang, Xiangyu
Qi, Xiaojuan
Computer Vision and Pattern Recognition
Artificial Intelligence
Vanilla autoregressive image generation models generate visual tokens step-by-step, limiting their ability to capture holistic relationships among token sequences. Moreover, because most visual tokenizers map local image patches into latent tokens, global information is limited. To address this, we introduce \textit{Hita}, a novel image tokenizer for autoregressive (AR) image generation. It introduces a holistic-to-local tokenization scheme with learnable holistic queries and local patch tokens. Hita incorporates two key strategies to better align with the AR generation process: 1) {arranging} a sequential structure with holistic tokens at the beginning, followed by patch-level tokens, and using causal attention to maintain awareness of previous tokens; and 2) adopting a lightweight fusion module before feeding the de-quantized tokens into the decoder to control information flow and prioritize holistic tokens. Extensive experiments show that Hita accelerates the training speed of AR generators and outperforms those trained with vanilla tokenizers, achieving \textbf{2.59 FID} and \textbf{281.9 IS} on the ImageNet benchmark. Detailed analysis of the holistic representation highlights its ability to capture global image properties, such as textures, materials, and shapes. Additionally, Hita also demonstrates effectiveness in zero-shot style transfer and image in-painting. The code is available at \href{https://github.com/CVMI-Lab/Hita}{https://github.com/CVMI-Lab/Hita}.
title Hita: Holistic Tokenizer for Autoregressive Image Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.02358