发表机构
The University of Texas at Austin; Reve（德克萨斯大学奥斯汀分校; 瑞夫）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对像素空间扩散中单一表示兼顾全局与细节的问题，提出双分支子补丁像素扩散变换器DuSPiT。通过分离全局与局部处理，利用两分支交互，实现更丰富细节和更好质量效率权衡，优于此前的像素空间扩散变换器。
AI 中文摘要
扩散变换器在图像生成方面性能强大，但大多在压缩潜在空间中运行。像素空间扩散可避免信息丢失，然而现有方法将每个原始图像补丁映射到单个令牌，使单一表示既要处理全局通信又要兼顾细粒度细节。我们提出新架构DuSPiT（双分支子补丁像素变换器）来解决此问题。该模型将全局结构推理与局部外观建模分离，利用紧凑基础分支进行高效全局推理，并行的高容量像素分支（组织成子补丁组）保留详细外观，两分支通过交叉注意力交互。实验结果表明，DuSPiT生成的图像细节更丰富、细粒度结构更强，且在质量-效率权衡上优于先前的像素空间扩散变换器。
英文摘要
Diffusion Transformers achieve strong image generation performance, but most operate in compressed latent spaces. Pixel-space diffusion avoids this information loss, yet existing approaches map each raw image patch to a single token, forcing one representation to handle both global communication and fine-grained details. We address this issue by proposing a new architecture, \textbf{DuSPiT}, a \textbf{Du}al-branch \textbf{S}ub\textbf{P}atch \textbf{Pi}xel \textbf{T}ransformer. This model separates global structural reasoning from local appearance modeling. DuSPiT uses a compact base branch for efficient global reasoning and a parallel, high-capacity pixel branch, organized into subpatch groups, to preserve detailed appearance, with the two branches interacting through cross-attention. Our results show that DuSPiT generates images with richer details and stronger fine-grained structures, while also achieving a better quality--efficiency trade-off than prior pixel-space diffusion transformers.
