Effective Diffusion Transformer Architecture for Image Super-Resolution

Kun Cheng* ¹  Lei Yu* ²  Zhijun Tu ²  Xiao He ¹  Liyu Chen ² 
Yong Guo ³  Mingrui Zhu ¹  Nannan Wang ¹  Xinbo Gao ⁴  Jie Hu ² 

¹ Xidian University   ² Huawei Noah's Ark Lab  
³ CBG, Huawei   ⁴ Chongqing University of Posts and Telecommunications

Introduction

We propose DiT-SR, an effective diffusion transformer architecture for real-world image super resolution:

• Effective yet efficient DiT architecture design;
• Adaptive Frequence Modulation (AdaFM) for diffusion time step.