Abstract
We introduce QuadTok, a novel framework for visual tokenization and autoregressive image generation. Compared to traditional approaches using 2D grids or 1D token sequences, we propose a hierarchical quadtree structure, bridging the gap between 2D spatial binding and 1D sequence-level flexibility. The QuadTok tokenizer dynamically allocates representational capacity to visually intricate areas while leaving homogeneous regions at a coarse resolution. Compared with a fixed 256-token grid, our ImageNet-trained tokenizer saves approximately 10% of tokens on ImageNet and 9% when transferred zero-shot to the COCO dataset, while maintaining comparable reconstruction fidelity. Furthermore, the natural causality introduced by the tree structure seamlessly enables autoregressive image generation. Conditioned on a quadtree topology supplied before generation, our 947M GPT-style generative model achieves a 2.08 gFID on the ImageNet $256 \times 256$ benchmark. Additionally, leveraging the strong spatial correlation preserved by the quadtree structure, the QuadTok generator enables zero-shot spatially controlled image generation capabilities. Code: https://github.com/myc634/QuadTok.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Mao, Y., Chen, Z., Shan, X., Zhang, X., Srivastava, D., Li, B., & Tu, Z. (2026). QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation. https://omanscience.com/en/articles/quadtok-quadtree-visual-tokenizer-for-autoregressive-image-generation
MLA 9
Mao, Yucheng, et al. "QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation." https://omanscience.com/en/articles/quadtok-quadtree-visual-tokenizer-for-autoregressive-image-generation.
Chicago (author–date)
Mao, Yucheng, Zeyuan Chen, Xiaojun Shan, Xiang Zhang, Divyansh Srivastava, Bingnan Li, and Zhuowen Tu. 2026. "QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation." https://omanscience.com/en/articles/quadtok-quadtree-visual-tokenizer-for-autoregressive-image-generation.
Harvard
Mao, Y., Chen, Z., Shan, X., Zhang, X., Srivastava, D., Li, B. and Tu, Z. (2026) 'QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation', Available at: https://omanscience.com/en/articles/quadtok-quadtree-visual-tokenizer-for-autoregressive-image-generation.
Vancouver
Mao Y, Chen Z, Shan X, Zhang X, Srivastava D, Li B, et al. QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation. https://omanscience.com/en/articles/quadtok-quadtree-visual-tokenizer-for-autoregressive-image-generation
IEEE
Y. Mao, Z. Chen, X. Shan, X. Zhang, D. Srivastava, B. Li, and Z. Tu, "QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation," https://omanscience.com/en/articles/quadtok-quadtree-visual-tokenizer-for-autoregressive-image-generation.