摘要
As the quality of mobile cameras starts to play a crucial role in modern smartphones, more and more attention is now being paid to ISP algorithms used to improve various perceptual aspects of mobile photos. In this Mobile AI challenge, 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. For this, the participants were provided with a novel learned ISP dataset consisting of RAW-RGB image pairs captured with the Sony IMX586 Quad Bayer mobile sensor and a professional 102-megapixel medium format camera. The runtime of all models was evaluated on the MediaTek Dimensity 1000+ platform with a dedicated AI processing unit capable of accelerating both floating-point and quantized neural networks. The proposed solutions are fully compatible with the above NPU and are capable of processing Full HD photos under 60-100 milliseconds while achieving high fidelity results. A detailed description of all models developed in this challenge is provided in this paper.
原文 | English |
---|---|
主出版物標題 | Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 |
發行者 | IEEE Computer Society |
頁面 | 2503-2514 |
頁數 | 12 |
ISBN(電子) | 9781665448994 |
DOIs | |
出版狀態 | Published - 2021 6月 |
事件 | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 - Virtual, Online, United States 持續時間: 2021 6月 19 → 2021 6月 25 |
出版系列
名字 | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
---|---|
ISSN(列印) | 2160-7508 |
ISSN(電子) | 2160-7516 |
Conference
Conference | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 |
---|---|
國家/地區 | United States |
城市 | Virtual, Online |
期間 | 21-06-19 → 21-06-25 |
All Science Journal Classification (ASJC) codes
- 電腦視覺和模式識別
- 電氣與電子工程