[2508.12811] Next Visual Granularity Generation

Computer Science > Computer Vision and Pattern Recognition arXiv:2508.12811 (cs) [Submitted on 18 Aug 2025 (v1), last revised 28 Feb 2026 (this version, v2)] Title:Next Visual Granularity Generation Authors:Yikai Wang, Zhouxia Wang, Zhonghua Wu, Qingyi Tao, Kang Liao, Chen Change Loy View a PDF of the paper titled Next Visual Granularity Generation, by Yikai Wang and 5 other authors View PDF HTML (experimental) Abstract:We propose a novel approach to image generation by decomposing an image into a structured sequence, where each element in the sequence shares the same spatial resolution but differs in the number of unique tokens used, capturing different level of visual granularity. Image generation is carried out through our newly introduced Next Visual Granularity (NVG) generation framework, which generates a visual granularity sequence beginning from an empty image and progressively refines it, from global layout to fine details, in a structured manner. This iterative process encodes a hierarchical, layered representation that offers fine-grained control over the generation process across multiple granularity levels. We train a series of NVG models for class-conditional image generation on the ImageNet dataset and observe clear scaling behavior. Compared to the VAR series, NVG consistently outperforms it in terms of FID scores (3.30 $\rightarrow$ 3.03, 2.57 $\rightarrow$ 2.44, 2.09 $\rightarrow$ 2.06). We also conduct extensive analysis to showcase the capability and po...