DeepAI AI Chat
Log In Sign Up

Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution

by   Zongcai Du, et al.

Runtime and memory consumption are two important aspects for efficient image super-resolution (EISR) models to be deployed on resource-constrained devices. Recent advances in EISR exploit distillation and aggregation strategies with plenty of channel split and concatenation operations to make full use of limited hierarchical features. In contrast, sequential network operations avoid frequently accessing preceding states and extra nodes, and thus are beneficial to reducing the memory consumption and runtime overhead. Following this idea, we design our lightweight network backbone by mainly stacking multiple highly optimized convolution and activation layers and decreasing the usage of feature fusion. We propose a novel sequential attention branch, where every pixel is assigned an important factor according to local and global contexts, to enhance high-frequency details. In addition, we tailor the residual block for EISR and propose an enhanced residual block (ERB) to further accelerate the network inference. Finally, combining all the above techniques, we construct a fast and memory-efficient network (FMEN) and its small version FMEN-S, which runs 33 faster and reduces 74 EISR model: E-RFDN, the champion in AIM 2020 efficient super-resolution challenge. Besides, FMEN-S achieves the lowest memory consumption and the second shortest runtime in NTIRE 2022 challenge on efficient super-resolution. Code is available at


page 6

page 7


Residual Local Feature Network for Efficient Super-Resolution

Deep learning based approaches has achieved great performance in single ...

Residual Feature Distillation Network for Lightweight Image Super-Resolution

Recent advances in single image super-resolution (SISR) explored the pow...

Edge-enhanced Feature Distillation Network for Efficient Super-Resolution

With the recently massive development in convolution neural networks, nu...

AsConvSR: Fast and Lightweight Super-Resolution Network with Assembled Convolutions

In recent years, videos and images in 720p (HD), 1080p (FHD) and 4K (UHD...

Efficient Multi-Purpose Cross-Attention Based Image Alignment Block for Edge Devices

Image alignment, also known as image registration, is a critical block u...

Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution

Convolutional neural networks based single-image super-resolution (SISR)...

Image Reconstruction of Multi Branch Feature Multiplexing Fusion Network with Mixed Multi-layer Attention

Image super-resolution reconstruction achieves better results than tradi...