EPISODE · Aug 20, 2025 · 22 MIN
Next Visual Granularity Generation
from Daily Paper Cast · host Jingwen Liang, Gengyu Wang
🤗 Upvotes: 37 | cs.CV, cs.AI, cs.LG Authors: Yikai Wang, Zhouxia Wang, Zhonghua Wu, Qingyi Tao, Kang Liao, Chen Change Loy Title: Next Visual Granularity Generation Arxiv: http://arxiv.org/abs/2508.12811v1 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 -> 3.03, 2.57 ->2.44, 2.09 -> 2.06). We also conduct extensive analysis to showcase the capability and potential of the NVG framework. Our code and models will be released.
What this episode covers
🤗 Upvotes: 37 | cs.CV, cs.AI, cs.LG Authors: Yikai Wang, Zhouxia Wang, Zhonghua Wu, Qingyi Tao, Kang Liao, Chen Change Loy Title: Next Visual Granularity Generation Arxiv: http://arxiv.org/abs/2508.12811v1 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 -> 3.03, 2.57 ->2.44, 2.09 -> 2.06). We also conduct extensive analysis to showcase the capability and potential of the NVG framework. Our code and models will be released.
NOW PLAYING
Next Visual Granularity Generation
No transcript for this episode yet
Similar Episodes
No similar episodes found.