Dataset

Metrics

Efficient Image Super-Resolution

• [SRCNN] 

• [FSRCNN] 

• [LapSRN] 

• [CARN] 

• [IMDN] 

• [RLFN] 

• [FMEN] 

• [SwinIR] 

• [Swin2SR] 

• [AsConvSR] 

• -  SRCNN [13] that applies deep learning to SISR for the first time.

• - FSRCNN [14] significantly accelerates the SISR network by adopting the original low-resolution as input without bicubic interpolation, smaller sizes of convolution kernels, and a deconvolution layer at the final stage of the network to perform upsampling.

• - LapSRN [27] progressively reconstructs the sub-band residuals of high-resolution images using the Laplacian pyramid.

• - CARN [2] further improves efficiency by its design of cascading residual networks with group convolution.

• - IMDN [21] proposes information multi-distillation blocks with contrast-aware attention (CCA) layer based on the information distillation mechanism, while RFDN [32] refines the architecture of RFDN with feature distillation mechanism by proposing the residual feature distillation block.

• - RLFN [25] redesigns RFDB by adding more channels to compensate for discarded feature distillation branches to achieve higher inference speed and better performance with fewer parameters.

• - FMEN [15] expands optimization space during training with re-parameterizable building blocks [12] without increasing extra inference time.

• - SwinIR [29] proposes an efficient transformer-based SR model which fully explores the swin transformer structure, and it outperforms pure convolution networks with fewer parameters and FLOPs.

• - Swin2SR [7] further improved the network structure by introducing the SwinV2 attention, and proposes auxiliary loss and high-frequency loss for the compressed images.

• 
  
• 
  

• C. Dong, C.C. Loy, K. He, and X. Tang, “Image Super-Resolution Using Deep Convolutional Networks,” In IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 295- 307, 2016.

• X. Chen, X. Wang, J. Zhou, Y. Qiao, and C. Dong, “Activating More Pixels In Image Super-Resolution Transformer, ” In Conference on Computer Vision and Pattern Recognition, pp. 22367-22377, 2023.

• W. Shi, J. Caballero, F. Huszar, J. Totz, A.P. Aitken, R. Bishop, D. Rueckert, and Z. Wang, “Real-Time Single Image And Video Super-Resolution Using An Efficient Sub-Pixel Convolutional Neural Network,” In Conference on Computer Vision and Pattern Recognition, pp. 1874-1883, 2016

• M.V. Conde, E. Zamfir, R. Timofte, D. Motilla, C. Liu, Z. Zhang, Y. Peng, Y. Lin, J. Guo, X. Zou, Y. Chen, Y. Liu, J. Hao, Y. Yan, Y. Zhang, G. Li, and L. Sun, “Efficient Deep Models For Real-Time 4K Image Super-Resolution NTIRE 2023 Benchmark And Report,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1495-1521, 2023.

• J. Guo, X. Zou, Y. Chen, Y. Liu, J. Hao, J. Liu, and Y. Yan, “AsConvSR: Fast And Lightweight Super-Resolution Network With Assembled Convolutions,” In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 1582-1592, 2023.

• L. Sun, J. Dong, J. Tang, and J. Pan, “Spatially-Adaptive Feature Modulation For Efficient Image Super-Resolution,” In Eprint ArXiv, 2302. 13800, 2023.

• [Bicubic++] B. B. Bilecen, M. Ayazoglu, "Bicubic++: Slim, Slimmer, Slimmest. Designing an Industry-Grade Super-Resolution Network", Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 1623-1632, 2023.