# OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling Network

arXiv: https://arxiv.org/abs/2008.02382 · HTML: https://mlsanity.com/paper/2008.02382/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Aug 2020.

## Built on by (most cited first, 15 of 15)

- [A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolution](https://mlsanity.com/paper/2112.04488/) (2021)
- [Continuous Remote Sensing Image Super-Resolution based on Context Interaction in Implicit Function Space](https://mlsanity.com/paper/2302.08046/) (2023)
- [Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors](https://mlsanity.com/paper/2407.09919/) (2024)
- [Lightweight Monocular Depth with a Novel Neural Architecture Search Method](https://mlsanity.com/paper/2108.11105/) (2021)
- [Lightweight Stepless Super-Resolution of Remote Sensing Images via Saliency-Aware Dynamic Routing Strategy](https://mlsanity.com/paper/2210.07598/) (2022)
- [Latent Diffusion, Implicit Amplification: Efficient Continuous-Scale Super-Resolution for Remote Sensing Images](https://mlsanity.com/paper/2410.22830/) (2024)
- [Scale-Aware Dynamic Network for Continuous-Scale Super-Resolution](https://mlsanity.com/paper/2110.15655/) (2021)
- [Effective Invertible Arbitrary Image Rescaling](https://mlsanity.com/paper/2209.13055/) (2022)
- [Your Super Resolution Model is not Enough for Tackling Real-World Scenarios](https://mlsanity.com/paper/2509.06387/) (2025)
- [Fast Neural Architecture Search for Lightweight Dense Prediction Networks](https://mlsanity.com/paper/2203.01994/) (2022)
- [Single Image Super-Resolution Based on Capsule Neural Networks](https://mlsanity.com/paper/2210.03743/) (2022)
- [A Scale-Arbitrary Image Super-Resolution Network Using Frequency-domain Information](https://mlsanity.com/paper/2212.04314/) (2022)
- [Learn From Orientation Prior for Radiograph Super-Resolution: Orientation Operator Transformer](https://mlsanity.com/paper/2312.16455/) (2023)
- [BasicAVSR: Arbitrary-Scale Video Super-Resolution via Image Priors and Enhanced Motion Compensation](https://mlsanity.com/paper/2510.26149/) (2025)
- [Implicit Neural Representation-Based Continuous Single Image Super-Resolution: An Empirical Benchmark](https://mlsanity.com/paper/2601.17723/) (2026)

## Abstract (arXiv)

Super-resolution (SR) has achieved great success due to the development of deep convolutional neural networks (CNNs). However, as the depth and width of the networks increase, CNN-based SR methods have been faced with the challenge of computational complexity in practice. Moreover, most of them train a dedicated model for each target resolution, losing generality and increasing memory requirements. To address these limitations we introduce OverNet, a deep but lightweight convolutional network to solve SISR at arbitrary scale factors with a single model. We make the following contributions: first, we introduce a lightweight recursive feature extractor that enforces efficient reuse of information through a novel recursive structure of skip and dense connections. Second, to maximize the performance of the feature extractor we propose a reconstruction module that generates accurate high-resolution images from overscaled feature maps and can be independently used to improve existing architectures. Third, we introduce a multi-scale loss function to achieve generalization across scales. Through extensive experiments, we demonstrate that our network outperforms previous state-of-the-art results in standard benchmarks while using fewer parameters than previous approaches.