# Journey Towards Tiny Perceptual Super-Resolution

arXiv: https://arxiv.org/abs/2007.04356 · HTML: https://mlsanity.com/paper/2007.04356/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2020.

## Built on by (most cited first, 27 of 27)

- [Fourier Space Losses for Efficient Perceptual Image Super-Resolution](https://mlsanity.com/paper/2106.00783/) (2021)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021)
- [Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances](https://mlsanity.com/paper/2209.13131/) (2022)
- [Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution](https://mlsanity.com/paper/2207.12577/) (2022)
- [Collapsible Linear Blocks for Super-Efficient Super Resolution](https://mlsanity.com/paper/2103.09404/) (2021)
- [ARM: Any-Time Super-Resolution Method](https://mlsanity.com/paper/2203.10812/) (2022)
- [RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization](https://mlsanity.com/paper/2205.05671/) (2022)
- [Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution](https://mlsanity.com/paper/2101.06658/) (2021)
- [Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables](https://mlsanity.com/paper/2303.14506/) (2023)
- [UDC: Unified DNAS for Compressible TinyML Models](https://mlsanity.com/paper/2201.05842/) (2022)
- [Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions](https://mlsanity.com/paper/2106.03727/) (2021)
- [GhostSR: Learning Ghost Features for Efficient Image Super-Resolution](https://mlsanity.com/paper/2101.08525/) (2021)
- [Differentiable Neural Architecture Search for Extremely Lightweight Image Super-Resolution](https://mlsanity.com/paper/2105.03939/) (2021)
- [Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-time Mobile Telepresence](https://mlsanity.com/paper/2304.11835/) (2023)
- [SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device](https://mlsanity.com/paper/2308.08137/) (2023)
- [When Visible-to-Thermal Facial GAN Beats Conditional Diffusion](https://mlsanity.com/paper/2302.09395/) (2023)
- [How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures](https://mlsanity.com/paper/2106.15021/) (2021)
- [RT-RCG: Neural Network and Accelerator Search Towards Effective and Real-time ECG Reconstruction from Intracardiac Electrograms](https://mlsanity.com/paper/2111.02569/) (2021)
- [Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation](https://mlsanity.com/paper/2212.07886/) (2022)
- [NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution](https://mlsanity.com/paper/2212.09501/) (2022)
- [Kernelized Back-Projection Networks for Blind Super Resolution](https://mlsanity.com/paper/2302.08478/) (2023)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [Temporal Kernel Consistency for Blind Video Super-Resolution](https://mlsanity.com/paper/2108.08305/) (2021)
- [A High-Performance Accelerator for Super-Resolution Processing on Embedded GPU](https://mlsanity.com/paper/2303.08999/) (2023)
- [High-Frequency Prior-Driven Adaptive Masking for Accelerating Image Super-Resolution](https://mlsanity.com/paper/2505.06975/) (2025)
- [ENAF: A Multi-Exit Network with an Adaptive Patch Fusion for Large Image Super Resolution](https://mlsanity.com/paper/2608.15349/) (2026)

## Abstract (arXiv)

Recent works in single-image perceptual super-resolution (SR) have demonstrated unprecedented performance in generating realistic textures by means of deep convolutional networks. However, these convolutional models are excessively large and expensive, hindering their effective deployment to end devices. In this work, we propose a neural architecture search (NAS) approach that integrates NAS and generative adversarial networks (GANs) with recent advances in perceptual SR and pushes the efficiency of small perceptual SR models to facilitate on-device execution. Specifically, we search over the architectures of both the generator and the discriminator sequentially, highlighting the unique challenges and key observations of searching for an SR-optimized discriminator and comparing them with existing discriminator architectures in the literature. Our tiny perceptual SR (TPSR) models outperform SRGAN and EnhanceNet on both full-reference perceptual metric (LPIPS) and distortion metric (PSNR) while being up to 26.4× more memory efficient and 33.6× more compute efficient respectively.