按频率分阶段生成图像，更快更高质量。
NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
- 按低频到高频顺序生成图像，贴合自然图像结构。
- ImageNet-256上FID达2.81，推理速度提升1.25倍。
- 适合追求高效高质图像生成的开发者与研究者。
自回归模型在图像生成中已取得显著成功。然而，标准自回归方法通常以固定空间顺序逐像素生成，未能利用图像信息在频域中的固有层次结构。为此，我们提出下一频率图像生成（NFIG），一种将生成过程分解为多个频率引导阶段的新框架。NFIG通过先生成低频成分来高效捕捉全局结构，再逐步添加高频细节，使生成过程更符合自然图像特性。该频率感知范式不仅提升了生成图像质量，还显著降低了推理成本，因早期即建立全局结构。在ImageNet-256基准上的大量实验验证了NFIG的有效性，其性能优于强基线VAR-d20（FID: 2.81），并实现1.25倍的速度提升。源代码见https://github.com/Pride-Huang/NFIG。
原文摘要 · Abstract (English)
Autoregressive models have achieved significant success in image generation. However, unlike the inherent hierarchical structure of image information in the spectral domain, standard autoregressive methods typically generate pixels sequentially in a fixed spatial order. To better leverage this spectral hierarchy, we introduce NextFrequency Image Generation (NFIG). NFIG is a novel framework that decomposes the image generation process into multiple frequency-guided stages. NFIG aligns the generation process with the natural image structure. It does this by first generating low-frequency components, which efficiently capture global structure with significantly fewer tokens, and then progressively adding higher-frequency details. This frequency-aware paradigm offers substantial advantages: it not only improves the quality of generated images but crucially reduces inference cost by efficiently establishing global structure early on. Extensive experiments on the ImageNet-256 benchmark validate NFIG's effectiveness, demonstrating superior performance (FID: 2.81) and a notable 1.25x speedup compared to the strong baseline VAR-d20. The source code is available at https://github.com/Pride-Huang/NFIG.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。