Video Quality Enhancement with Deep Neural Networks on Edge Devices: Architectures, Optimizations, and Challenges

• Garibaldi da Silveira Júnior UFPel
• Gilberto Kreisler UFPel
• Bruno Zatt UFPel
• Daniel Palomino UFPel
• Guilherme Correa UFPel

DOI: https://doi.org/10.5753/webmedia.2026.28949

Abstract

The growing demand for high-quality video content and the dominance of video traffic in modern networks have intensified the need for efficient video quality enhancement methods capable of operating on edge devices. Although deep neural networks have achieved state-of-the-art performance in tasks such as compression artifact reduction, denoising, and video super-resolution, most existing architectures rely on computationally expensive operations that hinder real-time deployment on resource-constrained platforms. This paper presents a systematic review of deep neural network based video quality enhancement architectures designed for edge devices, with a focus on real-time performance and efficiency–quality trade-offs. Existing approaches are analyzed by categorizing them into system-level video delivery frameworks and optimized neural models, highlighting key architectural choices, optimization strategies, and validation practices. The review reveals common trends, limitations, and open challenges, emphasizing that effective VQE on edge devices requires carefully balancing perceptual quality, computational complexity, memory usage, and energy consumption.

Keywords: Video Quality Enhancement, Deep Neural Networks, Edge Devices, Real-Time Processing

References

Benjamin Bross, Ye-Kui Wang, Yan Ye, Shan Liu, Jianle Chen, Gary J Sullivan, and Jens-Rainer Ohm. 2021. Overview of the versatile video coding (VVC) standard and its applications. IEEE Transactions on Circuits and Systems for Video Technology 31, 10 (2021), 3736–3764.

Jose Caballero, Christian Ledig, Andrew Aitken, Alejandro Acosta, Johannes Totz, Zehan Wang, and Wenzhe Shi. 2017. Real-time video super-resolution with spatio-temporal networks and motion compensation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4778–4787.

Ekrem Çetinkaya, Minh Nguyen, and Christian Timmerer. 2022. LiDeR: Lightweight dense residual network for video super-resolution on mobile devices. In 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP). IEEE, 1–5.

Baili Chai, Di Wu, Jinyu Chen, Mengyu Yang, Zelong Wang, and Miao Hu. 2024. REM: Enabling Real-Time Neural-Enhanced Video Streaming on Mobile Devices Using Macroblock-Aware Lookup Table. IEEE Transactions on Mobile Computing (2024).

Kelvin CK Chan, Xintao Wang, Ke Yu, Chao Dong, and Chen Change Loy. 2021. Basicvsr: The search for essential components in video super-resolution and beyond. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 4947–4956.

Jiasi Chen and Xukan Ran. 2019. Deep learning with edge computing: A review. Proc. IEEE 107, 8 (2019), 1655–1674.

Kemi Chen, Jing Chen, Huanqiang Zeng, and Xueyuan Shen. 2023. Fast-MFQE: A fast approach for multi-frame quality enhancement on compressed video. Sensors 23, 16 (2023), 7227.

Lvcheng Chen, Pingyang Liu, and Li Zhang. 2021. A Light-Weight Compressed Video Processing Method on Embedded Platforms for IIoT. In 2021 International Conference on Intelligent Technology and Embedded Systems (ICITES). IEEE, 8–13.

CISCO. 2020. Cisco Annual Internet Report (2018–2023) White Paper. Available online: [link]. Accessed: 2026-01-07.

Michele Claus and Jan Van Gemert. 2019. Videnn: Deep blind video denoising. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops. 0–0.

Garibaldi da Silveira Júnior, Gilberto Kreisler, Bruno Zatt, Daniel Palomino, and Guilherme Correa. 2024. Multi-Domain Spatio-Temporal Deformable Fusion model for video quality enhancement. In Brazilian Symposium on Multimedia and the Web (WebMedia). SBC, 223–230.

Garibaldi da Silveira Júnior, Bruno Zatt, Daniel Palomino, and Guilherme Correa. 2025. 4D-STDF: Compressed Video Quality Enhancement with 3D Spatio-Temporal Fusion and Deformable Convolution. In Brazilian Symposium on Multimedia and the Web (WebMedia). SBC, 491–495.

Jianing Deng, Shunjie Dong, Lvcheng Chen, Jingtong Hu, and Cheng Zhuo. 2024. Stdf: Spatio-temporal deformable fusion for video quality enhancement on embedded platforms. ACM Transactions on Embedded Computing Systems 23, 2 (2024), 1–25.

Jianing Deng, Li Wang, Shiliang Pu, and Cheng Zhuo. 2020. Spatio-temporal deformable convolution for compressed video quality enhancement. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 10696–10703.

Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. 2014. Learning a Deep Convolutional Network for Image Super-Resolution. In European Conference on Computer Vision (ECCV). 184–199. DOI: 10.1007/978-3-319-10593-2_13

Xuyang Duan, Zikang Zhou, Wu Qiu, Zhiyi Shu, Zheng Tang, and Jun Han. 2024. A Hardware-Aware and Content-Adaptive Super Resolution System for Bandwidth-Limited IoT Video Delivery. In Proceedings of the 14th International Conference on the Internet of Things. 19–27.

Zhijie Huang, Jun Sun, and Xiaopeng Guo. 2023. FastCNN: Towards fast and accurate spatiotemporal network for HEVC compressed video enhancement. ACM Transactions on Multimedia Computing, Communications and Applications 19, 3 (2023), 1–22.

Andrey Ignatov, Andres Romero, Heewon Kim, and Radu Timofte. 2021. Real-time video super-resolution on smartphones with deep learning, mobile ai 2021 challenge: Report. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2535–2544.

Yuxuan Jiang, Jakub Nawała, Chen Feng, Fan Zhang, Xiaoqing Zhu, Joel Sole, and David Bull. 2025. RTSR: A real-time super-resolution model for av1 compressed content. In 2025 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 1–5.

Ilhwan Kwon, Jun Li, and Mukesh Prasad. 2023. Lightweight video super-resolution for compressed video. Electronics 12, 3 (2023), 660.

Chulhee Lee, Seungdeuk Cho, Jihwan Choe, Taeuk Jeong, Wonsuk Ahn, and Eunjae Lee. 2006. Objective video quality assessment. Optical engineering 45, 1 (2006), 017004.

Na Li, Zichen Zhu, Sheng Wei, and Yao Liu. 2025. EVASR: Edge-Based Salience-Aware Super-Resolution for Enhanced Video Quality and Power Efficiency. ACM Transactions on Multimedia Computing, Communications and Applications (2025).

Hongying Liu, Zhubo Ruan, Peng Zhao, Chao Dong, Fanhua Shang, Yuanyuan Liu, Linlin Yang, and Radu Timofte. 2022. Video super-resolution based on deep learning: a comprehensive survey. Artificial Intelligence Review 55, 8 (2022), 5981–6035.

Shaoli Liu, Chengjian Zheng, Kaidi Lu, Si Gao, Ning Wang, Bofei Wang, Diankai Zhang, Xiaofeng Zhang, and Tianyu Xu. 2021. Evsrnet: Efficient video super-resolution with neural architecture search. In Proceedings of the ieee/cvf conference on computer vision and pattern recognition. 2480–2485.

Xilai Liu, Zhihui Ke, Xiaobo Zhou, Tie Qiu, and Keqiu Li. 2022. QoE-oriented adaptive video streaming with edge-client collaborative super-resolution. In GLOBECOM 2022-2022 IEEE Global Communications Conference. IEEE, 6158–6163.

Laigan Luo, Benshun Yi, Zhongyuan Wang, Peng Yi, and Zheng He. 2024. Efficient lightweight network for video super-resolution. Neural Computing and Applications 36, 2 (2024), 883–896.

Prayushi Mathur, Ashish Kumar Singh, Syed Azeemuddin, Jayram Adoni, and Prasad Adireddy. 2021. A real-time super-resolution for surveillance thermal cameras using optimized pipeline on embedded edge device. In 2021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE, 1–7.

Sachin Mehta, Amit Kumar, Fitsum Reda, Varun Nasery, Vikram Mulukutla, Rakesh Ranjan, and Vikas Chandra. 2021. Evrnet: Efficient video restoration on edge devices. In Proceedings of the 29th ACM international conference on multimedia. 983–992.

Netflix Tech Blog. 2022. All of Netflix’s HDR video streaming is now dynamically optimized. Available online: [link]. Accessed: 2026-01-07.

Seonghoon Park, Minchan Kim, Hyejin Park, Jeho Lee, Jiwon Kim, and Hojung Cha. 2025. EOS: Energy-Optimized Super-Resolution on Mobile Devices for Live 360-Degree Videos. In Proceedings of the 31st Annual International Conference on Mobile Computing and Networking. 878–893.

Arti Ranjan and M Ravinder. 2025. UNetDeblur: Optimized Lightweight and Efficient Motion Deblurring for Mobile Platforms in Real-Time Scenarios. Circuits, Systems, and Signal Processing (2025), 1–34.

Reza Rassool. 2017. VMAF reproducibility: Validating a perceptual practical video quality metric. In Proceedings of 2017 IEEE international symposium on broadband multimedia systems and broadcasting (BMSB). IEEE, IEEE, Piscataway, NJ, USA, 1–2.

Amirhossein Sadough, Mahyar Shahsavari, Mark Wijtvliet, and Marcel van Gerven. 2025. ELVSR: An efficient and lightweight convolutional neural network for FPGA-Based FHD to UHD video super-resolution. Array (2025), 100542.

Amirhossein Sadough, Mahyar Shahsavari, Mark Wijtvliet, and Marcel AJ van Gerven. 2024. ELVSR: An Efficient and Lightweight Convolutional Neural Network for FPGA-Based FHD to UHD Video Super-Resolution. Available at SSRN 5150107 (2024).

I Sandvine. 2023. Global internet phenomena report. Available online: [link]. Accessed: 2026-01-07.

Sonia Victor Soans, T Prabakaran, and S Vamshi Krushna. 2025. AI-DRIVEN REAL-TIME VIDEO ENHANCEMENT USING SUPER-RESOLUTION AND OPTICAL FLOW TECHNIQUE. ICTACT Journal on Image & Video Processing 15, 3 (2025).

Yapeng Tian, Yulun Zhang, Yun Fu, and Chenliang Xu. 2020. Tdan: Temporally-deformable alignment network for video super-resolution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 3360–3369.

Federico Vaccaro, Marco Bertini, Tiberio Uricchio, and Alberto Del Bimbo. 2021. Fast video visual quality and resolution improvement using SR-UNet. In Proceedings of the 29th ACM International Conference on Multimedia. 1221–1229.

Fangxin Wang, Miao Zhang, Xiangxiang Wang, Xiaoqiang Ma, and Jiangchuan Liu. 2020. Deep learning for edge computing applications: A state-of-the-art survey. IEEE Access 8 (2020), 58322–58336.

Xintao Wang, Kelvin CK Chan, Ke Yu, Chao Dong, and Chen Change Loy. 2019. Edvr: Video restoration with enhanced deformable convolutional networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops. 0–0.

Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600–612.

Xinyi Wu, Santiago López-Tapia, Xijun Wang, Rafael Molina, and Aggelos K Katsaggelos. 2024. Real-time lightweight video super-resolution with RRED-based perceptual constraint. IEEE Transactions on Circuits and Systems for Video Technology 34, 10 (2024), 10310–10325.

Yushu Wu, Yifan Gong, Pu Zhao, Yanyu Li, Zheng Zhan, Wei Niu, Hao Tang, Minghai Qin, Bin Ren, and Yanzhi Wang. 2022. Compiler-aware neural architecture search for on-mobile real-time super-resolution. In European Conference on Computer Vision. Springer, 92–111.

Zhijiao Xiao, Zhikai Zhang, Kwok-Wai Hung, and Simon Lui. 2021. Real-time video super-resolution using lightweight depthwise separable group convolutions with channel shuffling. Journal of Visual Communication and Image Representation 75 (2021), 103038.

Tianyu Xu, Zhuang Jia, Yijian Zhang, Long Bao, and Heng Sun. 2022. Elsr: Extreme low-power super resolution network for mobile devices. arXiv preprint arXiv:2208.14600 (2022).

Ren Yang, Mai Xu, Zulin Wang, and Tianyi Li. 2018. Multi-frame quality enhancement for compressed video. In Proceedings of the IEEE conference on computer vision and pattern recognition. 6664–6673.

Xi Yang, Xindong Zhang, and Lei Zhang. 2023. Flow-guided deformable attention network for fast online video super-resolution. In 2023 IEEE International Conference on Image Processing (ICIP). IEEE, 390–394.

Hyunho Yeo, Chan Ju Chong, Youngmok Jung, Juncheol Ye, and Dongsu Han. 2020. Nemo: enabling neural-enhanced video streaming on commodity mobile devices. In Proceedings of the 26th Annual International Conference on Mobile Computing and Networking. 1–14.

Ke Yu, Chao Dong, Chen Change Loy, and Xiaoou Tang. 2016. Deep convolution networks for compression artifacts reduction. arXiv preprint arXiv:1608.02778 (2016).

Qian Yu, Qing Li, Rui He, Gareth Tyson, Wanxin Shi, Jianhui Lv, Zhenhui Yuan, Peng Zhang, Yulong Lan, and Zhicheng Li. 2023. BiSR: Bidirectionally optimized super-resolution for mobile video streaming. In Proceedings of the ACM Web Conference 2023. 3121–3131.

Jian Yue, Mao Ye, Luping Ji, Hongwei Guo, and Ce Zhu. 2025. A Survey of Deep-Learning-Based Compressed Video Quality Enhancement. IEEE Transactions on Broadcasting (2025).

Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, 586–595.

Xindong Zhang, Hui Zeng, and Lei Zhang. 2021. Edge-oriented convolution block for real-time super resolution on mobile devices. In Proceedings of the 29th ACM international conference on multimedia. 4034–4043.

Minyi Zhao, Yi Xu, and Shuigeng Zhou. 2021. Recursive fusion and deformable spatiotemporal attention for video compression artifact reduction. In Proceedings of the 29th ACM international conference on multimedia. 5646–5654.

Zhaowen Zheng, Yuqiao Huang, and Dihu Chen. 2024. A lightweight distillation recurrent convolution network on FPGA for real-time video super-resolution. Multimedia Systems 30, 6 (2024), 318.