DreamSR：基于感受野增强扩散 Transformer 的超高分辨率图像超分辨率
DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformer
针对大分辨率图像分块推理时全局提示词与局部图像块语义错位导致的过度生成问题，提出双分支 MM-ControlNet：用图像块级提示词生成局部文本特征、用全局提示词提供全局文本特征，并配合感受野增强训练策略；这套「全局-局部提示词对齐 + 感受野增强」思路可直接迁移到其他基于扩散模型的大图分块生成任务（如修复、编辑）。
原文依据 we propose a dual-branch MM-ControlNet, where the ControlNet generates local textual feature with patch-level prompts
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论大规模预训练扩散模型凭借其通过文本引导获得的强大生成先验，已被广泛用于真实世界图像超分辨率。然而，在采用分块推理策略对高分辨率图像进行超分辨率时，大多数现有基于扩散的超分辨率方法往往会出现过度生成，其原因在于每次推理步骤中来自低分辨率图像的全局提示词与局部图像块不完整的语义信息之间存在错位。另一方面，由于网络设计与训练策略过度强调全局生成能力，大多数现有方法也难以在局部图像块中生成细节纹理。为解决这一问题，本文提出 DreamSR，一种新的超分辨率模型，它抑制局部过度生成并提升精细细节的合成能力，从而获得细节质量极高、视觉上忠实的结果。具体而言，我们提出双分支 MM-ControlNet，其中 ControlNet 利用图像块级提示词生成局部文本特征，而预训练的 DiT 利用全局提示词提供全局文本特征，从而缓解过度生成并保证各图像块之间的语义一致性。我们还设计了一套完整的训练策略，包含分阶段的数据处理流程以及感受野增强策略，增强了模型捕获图像块信息并有效恢复局部纹理的能力。大量实验表明，DreamSR 优于最优方法，能够提供高质量的超分辨率结果。
英文原文摘要 1560 字符
Large-scale pre-trained diffusion models have been extensively adopted for real-world image Super-Resolution because of their powerful generative priors through textual guidance. However, when super-resolving high-resolution images with patch-wise inference strategy, most existing diffusion-based SR methods tend to suffer from over-generation, due to the misalignment between the global prompt from LR image and the incomplete semantic information of local patches during each inference step. On the other hand, most existing methods also failed to generate detailed texture in local patches due to the overemphasis on global generation capabilities in network designs and training strategies.To address this issue, we present DreamSR, a novel SR model that suppresses local over-generation and improves fine-detail synthesis, thereby achieving visually faithful results with ultra-high-quality details. Specifically, we propose a dual-branch MM-ControlNet, where the ControlNet generates local textual feature with patch-level prompts while the pre-trained DiT provides global textual feature with global prompts, thereby mitigating over-generation and ensuring semantic consistency across patches.We also design a comprehensive training strategy with stage-specific data processing pipelines and a Receptive-Field Enhancement strategy, enhancing the model's capability to capture patch information and effectively restore local textures.Extensive experiments demonstrate that DreamSR outperforms state-of-the-art methods, providing high-quality SR results.