Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report

@article{Ignatov2021FastAA,
  title={Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report},
  author={Andrey D. Ignatov and Grigory Malivenko and R. Timofte and Sheng Chen and Xin Xia and Zhaoyang Liu and Yuwei Zhang and Feng Zhu and Jiashi Li and XueFeng Xiao and Yuan Tian and Xinglong Wu and C. Kyrkou and Yixin Chen and Zexin Zhang and Yunbo Peng and Yue Lin and S. Dutta and Sourya Dipta Das and Nisarg A. Shah and Himanshu Kumar and Chao Ge and Pei Wu and Jin-Hua Du and Andrew Batutin and Juan Pablo Federico and Konrad Lyda and Levon Khojoyan and Abhishek Thanki and Sayak Paul and Shahid Siddiqui},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2021},
  pages={2558-2568}
}
Camera scene detection is among the most popular computer vision problem on smartphones. While many custom solutions were developed for this task by phone vendors, none of the designed models were available publicly up until now. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms. For this, the… Expand
Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report
TLDR
This paper introduces the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly realtime performance on smartphones and IoT platforms. Expand
Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
  • Andrey D. Ignatov, Kim Byeoung-su, +29 authors Feifei Chen
  • Computer Science, Engineering
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2021
TLDR
The first Mobile AI challenge is introduced, where the target is to develop an end-to-end deep learning-based image denoising solution that can demonstrate high efficiency on smartphone GPUs. Expand
Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report
TLDR
The target was to develop an end-to-end deep learning-based image signal processing (ISP) pipeline that can replace classical hand-crafted ISPs and achieve nearly real-time performance on smartphone NPUs. Expand
Fast and Accurate Camera Scene Detection on Smartphones
TLDR
A novel Camera Scene Detection Dataset (CamSDD) containing more than 11K manually crawled images belonging to 30 different scene categories is proposed and an efficient and NPU-friendly CNN model is proposed that demonstrates a top-3 accuracy of 99.5% on this dataset and achieves more than 200 FPS on the recent mobile SoCs. Expand
Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report
  • Andrey D. Ignatov, R. Timofte, +20 authors Shengpeng Wang
  • Computer Science, Engineering
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2021
TLDR
The first Mobile AI challenge is introduced, where the target is to develop an end-to-end deep learning-based image super-resolution solutions that can demonstrate a real-time performance on mobile or edge NPUs. Expand
Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report
TLDR
The target is to develop an end-to-end deep learning-based video super-resolution solutions that can achieve a realtime performance on mobile GPUs and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results. Expand

References

SHOWING 1-10 OF 46 REFERENCES
Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report
TLDR
This paper introduces the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly realtime performance on smartphones and IoT platforms. Expand
Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
  • Andrey D. Ignatov, Kim Byeoung-su, +29 authors Feifei Chen
  • Computer Science, Engineering
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2021
TLDR
The first Mobile AI challenge is introduced, where the target is to develop an end-to-end deep learning-based image denoising solution that can demonstrate high efficiency on smartphone GPUs. Expand
Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report
TLDR
The target was to develop an end-to-end deep learning-based image signal processing (ISP) pipeline that can replace classical hand-crafted ISPs and achieve nearly real-time performance on smartphone NPUs. Expand
Fast and Accurate Camera Scene Detection on Smartphones
TLDR
A novel Camera Scene Detection Dataset (CamSDD) containing more than 11K manually crawled images belonging to 30 different scene categories is proposed and an efficient and NPU-friendly CNN model is proposed that demonstrates a top-3 accuracy of 99.5% on this dataset and achieves more than 200 FPS on the recent mobile SoCs. Expand
Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report
  • Andrey D. Ignatov, R. Timofte, +20 authors Shengpeng Wang
  • Computer Science, Engineering
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2021
TLDR
The first Mobile AI challenge is introduced, where the target is to develop an end-to-end deep learning-based image super-resolution solutions that can demonstrate a real-time performance on mobile or edge NPUs. Expand
Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report
TLDR
The target is to develop an end-to-end deep learning-based video super-resolution solutions that can achieve a realtime performance on mobile GPUs and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results. Expand
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
TLDR
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones and proposes solutions that significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones. Expand
AI Benchmark: Running Deep Neural Networks on Android Smartphones
TLDR
A study of the current state of deep learning in the Android ecosystem and describe available frameworks, programming models and the limitations of running AI on smartphones, as well as an overview of the hardware acceleration resources available on four main mobile chipset platforms. Expand
AI Benchmark: All About Deep Learning on Smartphones in 2019
TLDR
This paper evaluates the performance and compares the results of all chipsets from Qualcomm, HiSilicon, Samsung, MediaTek and Unisoc that are providing hardware acceleration for AI inference and discusses the recent changes in the Android ML pipeline. Expand
Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latency
TLDR
This is the first paper that addresses all the deployment issues of image deblurring task across mobile devices, and is adopted by the championship-winning team in NTIRE 2020 Image Deblurring Challenge on Smartphone Track. Expand
...
1
2
3
4
5
...