提出时间感知扩散模型，提升图像超分辨率的保真与细节
TASR: Timestep-Aware Diffusion Model for Image Super-Resolution
- 根据噪声去除阶段动态调整低分辨率信息注入
- 在早期增强图像保真度，后期提升细节生成能力
- 适合追求高质量超分效果的研究者和开发者
扩散模型在图像超分辨率领域取得显著进展，现有方法通常通过ControlNet注入低分辨率（LR）图像。本文首次研究ControlNet中信息注入的时间动态性，发现LR输入主要影响去噪过程的初始阶段。基于此，我们提出一种新型时间感知扩散模型，自适应融合ControlNet与预训练Stable Diffusion（SD）的特征。该方法在扩散初期强化LR信息传递以保障图像保真度，后期激发SD自身生成能力以增强细节。为训练该模型，我们设计了时间感知训练策略，针对不同时间步采用差异化损失并作用于不同模块。在基准数据集上的实验验证了方法的有效性。代码已开源。
原文摘要 · Abstract (English)
Diffusion models have recently achieved outstanding results in the field of image super-resolution. These methods typically inject low-resolution (LR) images via ControlNet.In this paper, we first explore the temporal dynamics of information infusion through ControlNet, revealing that the input from LR images predominantly influences the initial stages of the denoising process. Leveraging this insight, we introduce a novel timestep-aware diffusion model that adaptively integrates features from both ControlNet and the pre-trained Stable Diffusion (SD). Our method enhances the transmission of LR information in the early stages of diffusion to guarantee image fidelity and stimulates the generation ability of the SD model itself more in the later stages to enhance the detail of generated images. To train this method, we propose a timestep-aware training strategy that adopts distinct losses at varying timesteps and acts on disparate modules. Experiments on benchmark datasets demonstrate the effectiveness of our method. Code: https://github.com/SleepyLin/TASR
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。