# MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors

arXiv: https://arxiv.org/abs/1908.07985 · HTML: https://mlsanity.com/paper/1908.07985/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2019.

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

- [Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions](https://mlsanity.com/paper/2106.05022/) (2021)
- [Fast On-device LLM Inference with NPUs](https://mlsanity.com/paper/2407.05858/) (2024)
- [LLMCad: Fast and Scalable On-device Large Language Model Inference](https://mlsanity.com/paper/2309.04255/) (2023)
- [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021)
- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution](https://mlsanity.com/paper/2207.12577/) (2022)
- [SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile](https://mlsanity.com/paper/2404.13528/) (2024)
- [Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions](https://mlsanity.com/paper/2106.03727/) (2021)
- [edge-SR: Super-Resolution For The Masses](https://mlsanity.com/paper/2108.10335/) (2021)
- [OODIn: An Optimised On-Device Inference Framework for Heterogeneous Mobile Devices](https://mlsanity.com/paper/2106.04723/) (2021)
- [Turbo: Opportunistic Enhancement for Edge Video Analytics](https://mlsanity.com/paper/2207.00172/) (2022)
- [Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniques](https://mlsanity.com/paper/2211.15751/) (2022)
- [Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting](https://mlsanity.com/paper/2303.08331/) (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)
- [SoD2: Statically Optimizing Dynamic Deep Neural Network](https://mlsanity.com/paper/2403.00176/) (2024)
- [SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices](https://mlsanity.com/paper/2101.07996/) (2021)
- [How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures](https://mlsanity.com/paper/2106.15021/) (2021)
- [Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation](https://mlsanity.com/paper/2212.07886/) (2022)
- [Domain Adaptation for Inertial Measurement Unit-based Human Activity Recognition: A Survey](https://mlsanity.com/paper/2304.06489/) (2023)
- [Optimizing 3D Gaussian Splattering for Mobile GPUs](https://mlsanity.com/paper/2511.16298/) (2025)
- [NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution](https://mlsanity.com/paper/2212.09501/) (2022)
- [Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generation](https://mlsanity.com/paper/2307.13412/) (2023)
- [Energy-Aware Dynamic Neural Inference](https://mlsanity.com/paper/2411.02471/) (2024)
- [AdaEnlight: Energy-aware Low-light Video Stream Enhancement on Mobile Devices](https://mlsanity.com/paper/2211.16135/) (2022)
- [HR Human: Modeling Human Avatars with Triangular Mesh and High-Resolution Textures from Videos](https://mlsanity.com/paper/2405.11270/) (2024)
- [Crafting Query-Aware Selective Attention for Single Image Super-Resolution](https://mlsanity.com/paper/2504.06634/) (2025)
- [PERTINENCE: Input-based Opportunistic Neural Network Dynamic Execution](https://mlsanity.com/paper/2507.01695/) (2025)

## Abstract (arXiv)

In recent years, convolutional networks have demonstrated unprecedented performance in the image restoration task of super-resolution (SR). SR entails the upscaling of a single low-resolution image in order to meet application-specific image quality demands and plays a key role in mobile devices. To comply with privacy regulations and reduce the overhead of cloud computing, executing SR models locally on-device constitutes a key alternative approach. Nevertheless, the excessive compute and memory requirements of SR workloads pose a challenge in mapping SR networks on resource-constrained mobile platforms. This work presents MobiSR, a novel framework for performing efficient super-resolution on-device. Given a target mobile platform, the proposed framework considers popular model compression techniques and traverses the design space to reach the highest performing trade-off between image quality and processing speed. At run time, a novel scheduler dispatches incoming image patches to the appropriate model-engine pair based on the patch's estimated upscaling difficulty in order to meet the required image quality with minimum processing latency. Quantitative evaluation shows that the proposed framework yields on-device SR designs that achieve an average speedup of 2.13x over highly-optimized parallel difficulty-unaware mappings and 4.79x over highly-optimized single compute engine implementations.