Searching Efficient Model-Guided Deep

Network for Image Denoising


Qian Ning1       Weisheng Dong1*    Xin Li2    Jinjian Wu1

1School of Artificial Intelligence, Xidian University          2West Virginia University





Figure 1. (a) The overall architecture of the proposed network; (b)-(d) a list of candidate operations to be searched for NL, DSL, and USL, respectively; (e) network depth searching; (f) layer operations searching; (g) network width searching.





Unlike the success of neural architecture search (NAS) in high-level vision tasks, it remains challenging to find computationally efficient and memory-efficient solutions to low-level vision problems such as image restoration throughNAS. One of the fundamental barriers to differential NAS based image restoration is the optimization gap between the super-network and the sub-architectures, causing instability during the searching process. In this paper, we present a novel approach to fill this gap in image denoising application by connecting model-guided design (MoD) with NAS (MoDNAS). Specifically, we propose to construct a new search space under a model-guided framework and develop more stable and efficient differential search strategies. MoD-NAS employs a highly reusable width search strategy and a densely connected search block to automatically select the operations of each layer as well as network width and depth via gradient descent. During the search process, the proposed MoD-NAS remains stable because of the smoother search space designed under the model-guided framework. Experimental results on several popular datasets show that our MoD-NAS method has achieved at least comparable even better PSNR performance than current state-of-the-art methods with fewer parameters, fewer flops, and less testing time.





                TIP 2023                                



Qian Ning, Weisheng Dong*, Xin Li and Jinjian Wu, “Searching Efficient Model-guided Deep Network for Image Denoising,” IEEE Transactions on Image Processing (IEEE TIP), 2023.




  author={Ning, Qian and Dong, Weisheng and Li, Xin and Wu, Jinjian},

  journal={IEEE Transactions on Image Processing},

  title={Searching Efficient Model-Guided Deep Network for Image Denoising},

























Qian Ning, Email:

Weisheng Dong, Email: