用渐进棋盘顺序实现多尺度图像自回归生成的高效并行采样
Progressive Checkerboards for Autoregressive Multiscale Image Generation
- 采用固定渐进棋盘顺序，分层并行采样图像区域
- 相同串行步数下，不同缩放因子效果相近，稳定高效
- 适合追求高生成效率的自回归图像生成任务
自回归图像生成中，如何在保持序列依赖建模的前提下高效并行采样是一个关键挑战。现有方法或通过多尺度金字塔中的尺度间条件建模，或在单图内使用规则划分或随机顺序并行采样。本文提出一种基于渐进棋盘结构的固定采样顺序，可在每一尺度上从均匀分布的区域并行采样，确保四叉树划分各层级始终保持平衡。该策略同时支持尺度间与尺度内有效条件建模。有趣的是，我们发现，在平衡设置下，只要总串行步骤数一致，多种不同的尺度放大因子均能获得相似性能。在类条件 ImageNet 上，本方法在模型容量相当的情况下，性能媲美最新自回归系统，且采样步骤更少。
原文摘要 · Abstract (English)
A key challenge in autoregressive image generation is to efficiently sample independent locations in parallel, while still modeling mutual dependencies with serial conditioning. Some recent works have addressed this by conditioning between scales in a multiscale pyramid. Others have looked at parallelizing samples in a single image using regular partitions or randomized orders. In this work we examine a flexible, fixed ordering based on progressive checkerboards for multiscale autoregressive image generation. Our ordering draws samples in parallel from evenly spaced regions at each scale, maintaining full balance in all levels of a quadtree subdivision at each step. This enables effective conditioning both between and within scales. Intriguingly, we find evidence that in our balanced setting, a wide range of scale-up factors lead to similar results, so long as the total number of serial steps is constant. On class-conditional ImageNet, our method achieves competitive performance compared to recent state-of-the-art autoregressive systems with like model capacity, using fewer sampling steps.
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。