基于扩散损失的自回归图像生成中的条件误差优化

Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss

February 2, 2026

作者: Yucheng Zhou, Hao Li, Jianbing Shen

cs.AI

摘要

近期研究探索了自回归模型在图像生成中的应用并取得显著成果，同时将扩散模型与自回归框架相结合，通过扩散损失优化图像生成。本研究从理论角度分析了采用扩散损失的扩散模型与自回归模型，重点揭示了后者的优势。我们通过理论对比证明，在自回归扩散模型中采用块去噪优化能有效抑制条件误差，形成稳定的条件分布。分析还表明自回归条件生成过程可优化条件本身，使条件误差的影响呈指数级衰减。此外，我们基于最优传输理论提出了一种新颖的条件优化方法，以解决"条件不一致"问题。理论分析表明，将条件优化建模为Wasserstein梯度流可确保收敛至理想条件分布，从而有效缓解条件不一致现象。实验结果表明，本方法在性能上优于采用扩散损失的扩散模型与自回归模型。

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.