让扩散模型生成更高质量图像，通过感知质量自动调节细节。
Quality-Aware Modulation for Diffusion Transformers
- 引入轻量级质量感知模块，根据输入动态生成调制向量。
- 在不改动采样流程下，显著提升图像清晰度与一致性。
- 适合关注生成图像质量的视觉生成研究者使用。
现代文本到图像的扩散模型（如扩散Transformer，DiT）依赖时间步或提示嵌入来调节每个步骤的去噪强度。然而，这种调节仅传递噪声水平信息，缺乏对生成质量的感知，导致生成图像存在语义不一致、视觉不连贯和保真度不足的问题。本文提出质量表示模块（QRM），一个轻量级Transformer模块，基于现有模型输入学习质量感知表示，并生成一组调制向量 $M_{qrm}$。这些向量通过调整DiT块中的自适应归一化参数，将质量敏感信号注入去噪过程。QRM无需改变采样调度或扩散主干结构。实验包括对QRM训练损失与架构的消融分析，以及实证结果，均表明其在多个基准上持续提升图像质量。
原文摘要 · Abstract (English)
Modern text-to-image diffusion models, such as diffusion transformers (DiT), rely on timestep or prompt embeddings to modulate the strength of the denoising process in each timestep. While this modulation communicates the current noise level, it does not provide any quality-aware information, which can lead to generated images that are unaligned, visually inconsistent, and lacking in fidelity. In this paper, we propose the Quality Representation Module (QRM), a lightweight transformer module that learns a quality-aware representation based on existing model inputs, and produces a set of vectors $M_{qrm}$. These vectors adjust the adaptive LayerNorm modulation within the DiT transformer blocks, thereby injecting a quality-sensitive signal into the denoising parameters. The QRM introduces no significant changes to the sampling schedule or diffusion backbone. Experiments include ablations on QRM training losses and architectures, as well as empirical results demonstrating consistent image quality improvements over baseline DiT-based models.
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。