ELSR: Extreme Low-Power Super Resolution Network For Mobile Devices

• URL: http://arxiv.org/abs/2208.14600v1
• Date: Wed, 31 Aug 2022 02:32:50 GMT
• Title: ELSR: Extreme Low-Power Super Resolution Network For Mobile Devices
• Authors: Tianyu Xu, Zhuang Jia, Yijian Zhang, Long Bao, Heng Sun
• Abstract summary: We propose Extreme Low-Power Super Resolution (ELSR) network which only consumes a small amount of energy in mobile devices. Pretraining and finetuning methods are applied to boost the performance of the extremely tiny model. We achieve a competitive score of 90.9 with PSNR 27.34 dB and power 0.09 W/30FPS on the target MediaTek Dimensity 9000 plantform.
• Score: 4.759823735082844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the popularity of mobile devices, e.g., smartphone and wearable devices, lighter and faster model is crucial for the application of video super resolution. However, most previous lightweight models tend to concentrate on reducing lantency of model inference on desktop GPU, which may be not energy efficient in current mobile devices. In this paper, we proposed Extreme Low-Power Super Resolution (ELSR) network which only consumes a small amount of energy in mobile devices. Pretraining and finetuning methods are applied to boost the performance of the extremely tiny model. Extensive experiments show that our method achieves a excellent balance between restoration quality and power consumption. Finally, we achieve a competitive score of 90.9 with PSNR 27.34 dB and power 0.09 W/30FPS on the target MediaTek Dimensity 9000 plantform, ranking 1st place in the Mobile AI & AIM 2022 Real-Time Video Super-Resolution Challenge.

Related papers

• Benchmarking Deep Learning Models for Object Detection on Edge Computing Devices [0.0]
  We evaluate state-of-the-art object detection models, including YOLOv8 (Nano, Small, Medium), EfficientDet Lite (Lite0, Lite1, Lite2), and SSD (SSD MobileNet V1, SSDLite MobileDet) We deployed these models on popular edge devices like the Raspberry Pi 3, 4, and 5 with/without TPU accelerators, and Jetson Orin Nano, collecting key performance metrics such as energy consumption, inference time, and Mean Average Precision (mAP) Our findings highlight that lower mAP models such as SSD MobileNet V1 are more energy-efficient and faster in
  arXiv  Detail & Related papers  (2024-09-25T10:56:49Z)
• MicroISP: Processing 32MP Photos on Mobile Devices with Deep Learning [114.66037224769005]
  We present a novel MicroISP model designed specifically for edge devices. The proposed solution is capable of processing up to 32MP photos on recent smartphones using the standard mobile ML libraries. The architecture of the model is flexible, allowing to adjust its complexity to devices of different computational power.
  arXiv  Detail & Related papers  (2022-11-08T17:40:50Z)
• Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report [97.01510729548531]
  We propose a real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. Models were evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption.
  arXiv  Detail & Related papers  (2022-11-07T22:33:19Z)
• Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report [144.41960648643564]
  In this paper, we propose the participants to design an efficient quantized image super-resolution solution. The solution can demonstrate a real-time performance on mobile NPUs. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU.
  arXiv  Detail & Related papers  (2022-11-07T22:27:58Z)
• E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles [78.50123964690094]
  Unmanned Aerial Vehicles (UAVs) based video text spotting has been extensively used in civil and military domains. Our proposed energy-efficient video text spotting solution, dubbed as E2VTS, outperforms all previous methods by achieving a competitive tradeoff between energy efficiency and performance.
  arXiv  Detail & Related papers  (2022-06-05T22:43:17Z)
• Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report [135.69469815238193]
  Video super-resolution has become one of the most important mobile-related problems due to the rise of video communication and streaming services. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based video super-resolution solutions. The proposed solutions are fully compatible with any mobile GPU and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results.
  arXiv  Detail & Related papers  (2021-05-17T13:40:50Z)
• Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report [67.86837649834636]
  We introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image super-resolution solution. The proposed solutions are fully compatible with all major mobile AI accelerators and are capable of reconstructing Full HD images under 40-60 ms.
  arXiv  Detail & Related papers  (2021-05-17T13:34:15Z)
• Real-Time Video Inference on Edge Devices via Adaptive Model Streaming [9.101956442584251]
  Real-time video inference on edge devices like mobile phones and drones is challenging due to the high cost of Deep Neural Networks. We present Adaptive Model Streaming (AMS), a new approach to improving performance of efficient lightweight models for video inference on edge devices.
  arXiv  Detail & Related papers  (2020-06-11T17:25:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.