.png){kind=icon}
返回
AddSR: Accelerating diffusion-based blind super-resolution with adversarial diffusion distillation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.113012.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Blind super-resolution methods based on Stable Diffusion (SD) demonstrate impressive generative capabilities in reconstructing clear, high-resolution (HR) images with intricate details from low-resolution (LR) inputs. However, their practical applicability is often limited by poor efficiency, as they typically require tens or even dozens of sampling steps. Inspired by Adversarial Diffusion Distillation (ADD), we incorporate this approach to design a highly effective and efficient blind super-resolution method. Nonetheless, two challenges arise: First, the original ADD significantly reduces result fidelity, leading to a perception-distortion imbalance. Second, SD-based methods are sensitive to the quality of the conditioning input, while LR images often have complex degradation, which further hinders effectiveness. To address these issues, we introduce a Timestep-Adaptive ADD (TA-ADD) to mitigate the perception-distortion imbalance caused by the original ADD. Furthermore, we propose a prediction-based self-refinement strategy to estimate HR, which allows for the provision of more high-frequency information without the need for additional modules. Extensive experiments show that our method, AddSR, generates superior restoration results while being significantly faster than previous SD-based state-of-the-art models (e.g., 7 x faster than SeeSR).
Keyword:
Super-resolution
Diffusion model
Generative prior
Efficiency
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
KGSR: A kernel guided network for real-world blind super-resolutionKGSR: 一种用于现实世界盲超分辨率的内核引导网络.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Compressed image super-resolution based on invertible degradation and restoration基于可逆降质与恢复的压缩图像超分辨率Pattern Recognition
Pattern RecognitionIF7.6
PREAI
分享收藏SRDiff: Single image super-resolution with diffusion probabilistic modelsSRDiff: 具有扩散概率模型的单幅图像超分辨率NEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏SPAST: Arbitrary style transfer with style priors via pre-trained large-scale modelSPAST：基于预训练大规模模型的具有风格先验的任意风格迁移NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏分享收藏分享收藏 没有更多内容
没有更多内容