# RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization

arXiv: https://arxiv.org/abs/2205.05671 · HTML: https://mlsanity.com/paper/2205.05671/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 69 references that are in the map.
- First posted on arXiv 11 May 2022.

## Builds on (most cited first, 30 of 51)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Image Generation from Scene Graphs](https://mlsanity.com/paper/1804.01622/) (2018)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- [On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization](https://mlsanity.com/paper/1802.06509/) (2018)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Deep Unfolding Network for Image Super-Resolution](https://mlsanity.com/paper/2003.10428/) (2020)
- [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)

## Built on by (most cited first, 19 of 19)

- [DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models](https://mlsanity.com/paper/2307.02457/) (2023)
- [Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution](https://mlsanity.com/paper/2405.07023/) (2024)
- [Re-parameterizing Your Optimizers rather than Architectures](https://mlsanity.com/paper/2205.15242/) (2022)
- [Swift Parameter-free Attention Network for Efficient Super-Resolution](https://mlsanity.com/paper/2311.12770/) (2023)
- [Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach](https://mlsanity.com/paper/2401.05633/) (2024)
- [MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices](https://mlsanity.com/paper/2507.01838/) (2025)
- [ESDMR-Net: A Lightweight Network With Expand-Squeeze and Dual Multiscale Residual Connections for Medical Image Segmentation](https://mlsanity.com/paper/2312.10585/) (2023)
- [IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentions](https://mlsanity.com/paper/2404.00633/) (2024)
- [Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting](https://mlsanity.com/paper/2312.10588/) (2023)
- [Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues](https://mlsanity.com/paper/2409.14330/) (2024)
- [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://mlsanity.com/paper/2303.04336/) (2023)
- [Learning a Single Convolutional Layer Model for Low Light Image Enhancement](https://mlsanity.com/paper/2305.14039/) (2023)
- [RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction](https://mlsanity.com/paper/2212.10066/) (2022)
- [ASR: Attention-alike Structural Re-parameterization](https://mlsanity.com/paper/2304.06345/) (2023)
- [DSR: Towards Drone Image Super-Resolution](https://mlsanity.com/paper/2208.12327/) (2022)
- [ESTISR: Adapting Efficient Scene Text Image Super-resolution for Real-Scenes](https://mlsanity.com/paper/2306.02443/) (2023)
- [RepQ: Generalizing Quantization-Aware Training for Re-Parametrized Architectures](https://mlsanity.com/paper/2311.05317/) (2023)
- [Sebica: Lightweight Spatial and Efficient Bidirectional Channel Attention Super Resolution Network](https://mlsanity.com/paper/2410.20546/) (2024)
- [RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution](https://mlsanity.com/paper/2504.15649/) (2025)

## Abstract (arXiv)

This paper explores training efficient VGG-style super-resolution (SR) networks with the structural re-parameterization technique. The general pipeline of re-parameterization is to train networks with multi-branch topology first, and then merge them into standard 3x3 convolutions for efficient inference. In this work, we revisit those primary designs and investigate essential components for re-parameterizing SR networks. First of all, we find that batch normalization (BN) is important to bring training non-linearity and improve the final performance. However, BN is typically ignored in SR, as it usually degrades the performance and introduces unpleasant artifacts. We carefully analyze the cause of BN issue and then propose a straightforward yet effective solution. In particular, we first train SR networks with mini-batch statistics as usual, and then switch to using population statistics at the later training period. While we have successfully re-introduced BN into SR, we further design a new re-parameterizable block tailored for SR, namely RepSR. It consists of a clean residual path and two expand-and-squeeze convolution paths with the modified BN. Extensive experiments demonstrate that our simple RepSR is capable of achieving superior performance to previous SR re-parameterization methods among different model sizes. In addition, our RepSR can achieve a better trade-off between performance and actual running time (throughput) than previous SR methods. Codes will be available at https://github.com/TencentARC/RepSR.