# Wide Activation for Efficient and Accurate Image Super-Resolution

arXiv: https://arxiv.org/abs/1808.08718 · HTML: https://mlsanity.com/paper/1808.08718/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2018.

## Built on by (most cited first, 30 of 65)

- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs](https://mlsanity.com/paper/2106.14103/) (2021)
- [Blind Image Super-Resolution: A Survey and Beyond](https://mlsanity.com/paper/2107.03055/) (2021)
- [Are we ready for a new paradigm shift? A Survey on Visual Deep MLP](https://mlsanity.com/paper/2111.04060/) (2021)
- [UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution](https://mlsanity.com/paper/2103.12716/) (2021)
- [NTIRE 2021 Challenge on Image Deblurring](https://mlsanity.com/paper/2104.14854/) (2021)
- [NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2205.05675/) (2022)
- [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021)
- [Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices](https://mlsanity.com/paper/2105.10288/) (2021)
- [Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2112.08655/) (2021)
- [NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results](https://mlsanity.com/paper/2104.10781/) (2021)
- [NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results](https://mlsanity.com/paper/2106.03839/) (2021)
- [Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution](https://mlsanity.com/paper/2207.12577/) (2022)
- [ARM: Any-Time Super-Resolution Method](https://mlsanity.com/paper/2203.10812/) (2022)
- [SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning](https://mlsanity.com/paper/2306.14070/) (2023)
- [Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models](https://mlsanity.com/paper/2306.00714/) (2023)
- [Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network](https://mlsanity.com/paper/2212.14181/) (2022)
- [Attention-based Multi-Reference Learning for Image Super-Resolution](https://mlsanity.com/paper/2108.13697/) (2021)
- [Bayesian Image Super-Resolution with Deep Modeling of Image Statistics](https://mlsanity.com/paper/2204.00623/) (2022)
- [Hierarchical Neural Operator Transformer with Learnable Frequency-aware Loss Prior for Arbitrary-scale Super-resolution](https://mlsanity.com/paper/2405.12202/) (2024)
- [Physics-informed Deep Super-resolution for Spatiotemporal Data](https://mlsanity.com/paper/2208.01462/) (2022)
- [Pedestrian Detection in Low-Light Conditions: A Comprehensive Survey](https://mlsanity.com/paper/2401.07801/) (2024)
- [Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting](https://mlsanity.com/paper/2303.08331/) (2023)
- [DSRGAN: Detail Prior-Assisted Perceptual Single Image Super-Resolution via Generative Adversarial Networks](https://mlsanity.com/paper/2112.13191/) (2021)
- [Learning Detail-Structure Alternative Optimization for Blind Super-Resolution](https://mlsanity.com/paper/2212.01624/) (2022)
- [Deep learning architectural designs for super-resolution of noisy images](https://mlsanity.com/paper/2102.05105/) (2021)
- [ECLARE: Efficient cross-planar learning for anisotropic resolution enhancement](https://mlsanity.com/paper/2503.11787/) (2025)
- [VSpSR: Explorable Super-Resolution via Variational Sparse Representation](https://mlsanity.com/paper/2104.08575/) (2021)

## Abstract (arXiv)

In this report we demonstrate that with same parameters and computational budgets, models with wider features before ReLU activation have significantly better performance for single image super-resolution (SISR). The resulted SR residual network has a slim identity mapping pathway with wider ((2×) to (4×)) channels before activation in each residual block. To further widen activation ((6×) to (9×)) without computational overhead, we introduce linear low-rank convolution into SR networks and achieve even better accuracy-efficiency tradeoffs. In addition, compared with batch normalization or no normalization, we find training with weight normalization leads to better accuracy for deep super-resolution networks. Our proposed SR network textitWDSR achieves better results on large-scale DIV2K image super-resolution benchmark in terms of PSNR with same or lower computational complexity. Based on WDSR, our method also won 1st places in NTIRE 2018 Challenge on Single Image Super-Resolution in all three realistic tracks. Experiments and ablation studies support the importance of wide activation for image super-resolution. Code is released at: https://github.com/JiahuiYu/wdsrntire2018