# A High-Performance Accelerator for Super-Resolution Processing on Embedded GPU

arXiv: https://arxiv.org/abs/2303.08999 · HTML: https://mlsanity.com/paper/2303.08999/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 66 references that are in the map.
- First posted on arXiv 16 Mar 2023.

## Builds on (most cited first, 30 of 32)

- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration](https://mlsanity.com/paper/1809.11165/) (2018)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017)
- [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://mlsanity.com/paper/2004.09602/) (2020)
- [Data-Driven Sparse Structure Selection for Deep Neural Networks](https://mlsanity.com/paper/1707.01213/) (2017)
- [Feedback Network for Image Super-Resolution](https://mlsanity.com/paper/1903.09814/) (2019)
- [Unfolding the Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2010.02631/) (2020)
- [MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution](https://mlsanity.com/paper/2007.11803/) (2020)
- [LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond](https://mlsanity.com/paper/2105.10422/) (2021)
- [Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search](https://mlsanity.com/paper/1901.07261/) (2019)
- [FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge](https://mlsanity.com/paper/1904.04421/) (2019)
- [JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video](https://mlsanity.com/paper/1909.04391/) (2019)
- [RAISR: Rapid and Accurate Image Super Resolution](https://mlsanity.com/paper/1606.01299/) (2016)
- [Journey Towards Tiny Perceptual Super-Resolution](https://mlsanity.com/paper/2007.04356/) (2020)
- [Collapsible Linear Blocks for Super-Efficient Super Resolution](https://mlsanity.com/paper/2103.09404/) (2021)
- [Ternary Neural Networks with Fine-Grained Quantization](https://mlsanity.com/paper/1705.01462/) (2017)
- [Lightweight Image Super-Resolution with Adaptive Weighted Learning Network](https://mlsanity.com/paper/1904.02358/) (2019)

## Abstract (arXiv)

Recent years have witnessed impressive progress in super-resolution (SR) processing. However, its real-time inference requirement sets a challenge not only for the model design but also for the on-chip implementation. In this paper, we implement a full-stack SR acceleration framework on embedded GPU devices. The special dictionary learning algorithm used in SR models was analyzed in detail and accelerated via a novel dictionary selective strategy. Besides, the hardware programming architecture together with the model structure is analyzed to guide the optimal design of computation kernels to minimize the inference latency under the resource constraints. With these novel techniques, the communication and computation bottlenecks in the deep dictionary learning-based SR models are tackled perfectly. The experiments on the edge embedded NVIDIA NX and 2080Ti show that our method outperforms the state-of-the-art NVIDIA TensorRT significantly, and can achieve real-time performance.