FVAR：面向视觉自回归建模的下一聚焦预测
FVAR: Next-Focus Prediction for Visual Autoregressive Modeling
将视觉自回归生成中的均匀降采样金字塔替换为基于物理散焦核的渐进聚焦金字塔，从源头消除混叠，可直接用于改进 VAR 类模型的细节生成质量。
原文依据 we present FVAR, which reframes the paradigm from next-scale prediction to next-focus prediction
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉自回归模型通过在多尺度词元金字塔上进行下一尺度预测，实现了卓越的生成质量。然而，传统方法使用均匀尺度降采样来构建这些金字塔，导致混叠伪影，损害细节并引入不希望的锯齿和摩尔纹。为解决此问题，我们提出 FVAR，将范式从下一尺度预测重构为下一聚焦预测，模仿相机从模糊到清晰的自然对焦过程。我们的方法引入三项关键创新：1）下一聚焦预测范式，通过逐步减少模糊而非简单降采样来改造多尺度自回归；2）渐进重聚焦金字塔构建，使用物理一致的散焦核构建干净、无混叠的多尺度表示；3）高频残差学习，采用专门的残差教师网络在训练中有效融入混叠信息，同时保持部署简洁。具体而言，我们使用半径递减的散焦点扩散函数（PSF）核构建光学低通视图，创建平滑的从模糊到清晰的过渡，从源头消除混叠。为进一步增强细节生成，我们引入高频残差教师，从干净结构和混叠残差中学习，并将该知识蒸馏到普通 VAR 部署网络以实现无缝推理。在 ImageNet 上的大量实验表明，FVAR 大幅减少混叠伪影，改善细节保留，提升文本可读性，在完美兼容现有 VAR 框架的同时取得优越性能。
英文原文摘要 1740 字符
Visual autoregressive models achieve remarkable generation quality through next-scale predictions across multi-scale token pyramids. However, the conventional method uses uniform scale downsampling to build these pyramids, leading to aliasing artifacts that compromise fine details and introduce unwanted jaggies and moire patterns. To tackle this issue, we present FVAR, which reframes the paradigm from next-scale prediction to next-focus prediction, mimicking the natural process of camera focusing from blur to clarity. Our approach introduces three key innovations: 1) Next-Focus Prediction Paradigm that transforms multi-scale autoregression by progressively reducing blur rather than simply downsampling; 2) Progressive Refocusing Pyramid Construction that uses physics-consistent defocus kernels to build clean, alias-free multi-scale representations; and 3) High-Frequency Residual Learning that employs a specialized residual teacher network to effectively incorporate alias information during training while maintaining deployment simplicity. Specifically, we construct optical low-pass views using defocus point spread function (PSF) kernels with decreasing radius, creating smooth blur-to-clarity transitions that eliminate aliasing at its source. To further enhance detail generation, we introduce a High-Frequency Residual Teacher that learns from both clean structure and alias residuals, distilling this knowledge to a vanilla VAR deployment network for seamless inference. Extensive experiments on ImageNet demonstrate that FVAR substantially reduces aliasing artifacts, improves fine detail preservation, and enhances text readability, achieving superior performance with perfect compatibility to existing VAR frameworks.