用扩散损失优化自回归图像生成，有效缓解条件误差问题。
Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss
- 通过扩散损失实现分块去噪，稳定条件分布
- 条件误差随生成过程指数级衰减，提升生成质量
- 基于最优传输的条件精修方法，解决条件不一致问题
近期研究探索了自回归模型在图像生成中的应用，并结合扩散模型与自回归框架，通过扩散损失优化生成效果。本文对扩散模型与带扩散损失的自回归模型进行理论分析，揭示后者优势。理论比较表明，自回归模型中的分块去噪优化能有效缓解条件误差，实现稳定的条件分布。分析还显示，自回归条件生成会逐步精炼条件，使条件误差影响呈指数衰减。此外，提出一种基于最优传输（OT）理论的新条件精修方法，以应对“条件不一致”问题。理论上证明，将条件精修建模为Wasserstein梯度流可保证收敛至理想条件分布，有效缓解条件不一致。实验表明，该方法优于现有的扩散模型及带扩散损失的自回归方法。
原文摘要 · Abstract (English)
Recent studies have explored autoregressive models for image generation, with promising results, and have combined diffusion models with autoregressive frameworks to optimize image generation via diffusion losses. In this study, we present a theoretical analysis of diffusion and autoregressive models with diffusion loss, highlighting the latter's advantages. We present a theoretical comparison of conditional diffusion and autoregressive diffusion with diffusion loss, demonstrating that patch denoising optimization in autoregressive models effectively mitigates condition errors and leads to a stable condition distribution. Our analysis also reveals that autoregressive condition generation refines the condition, causing the condition error influence to decay exponentially. In addition, we introduce a novel condition refinement approach based on Optimal Transport (OT) theory to address ``condition inconsistency''. We theoretically demonstrate that formulating condition refinement as a Wasserstein Gradient Flow ensures convergence toward the ideal condition distribution, effectively mitigating condition inconsistency. Experiments demonstrate the superiority of our method over diffusion and autoregressive models with diffusion loss methods.
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。