AIM 2020 Challenge on Rendering Realistic Bokeh

Ignatov, Andrey; Timofte, Radu; Ming, Qian; Qiao, Congyu; Lin, Jiaxin; Guo, Zhenyu; Li, Chenghua; Leng, Cong; Cheng, Jian; Peng, Jiangde; Luo, Xianrui; Xian, Ke; Wu, Zijin; Cao, Zhiguo; Puthussery, Densen; Jiji, C. V.; Hrishikesh, P. S.; Kuriakose, Melvin; Dutta, Saikat; Das, Sourya Dipta; Shah, Nisarg; Purohit, Kuldeep; Kandula, Praveen; Suin, Maitreya; Rajagopalan, A. N.; Saagara, M. B.; Minnu, A. L.; Sanjana, A. R.; Praseeda, S.; Wu, Ge; Chen, Xueqin; Wang, Tengyao; Zheng, Max; Wong, Hulk; Zou, Jay

doi:10.1007/978-3-030-67070-2_13

Cited by 38 publications

(19 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the 2020 AIM challenge for rendering a realistic blur used a Canon 7D dSLR camera as a base and attempted to create similar images algorithmically with smartphone cameras. 64 The process for articulating blur and bokeh was introduced in 2014 and by 2016 was a common feature of most "portrait modes" of smartphone cameras. When Google's Pixel phone introduced an algorithm for mimicking shallow depth of field, they termed the effect "Lens Blur."…”

Section: The Continuity Aesthetic Of Blurmentioning

confidence: 99%

Portraiture, Surveillance, and the Continuity Aesthetic of Blur

Hristova¹

2021

Frames

View full text Add to dashboard Cite

Section: The Continuity Aesthetic Of Blurmentioning

confidence: 99%

Portraiture, Surveillance, and the Continuity Aesthetic of Blur

Hristova¹

2021

Frames

View full text Add to dashboard Cite

“…• Learned End-to-End ISP: [25,29] • Perceptual Image Enhancement: [28,22] • Bokeh Effect Rendering: [21,27] • Image Super-Resolution: [28,41,4,48] Hsyu, Wen-Chia Tsai, Chao-Wei Chen Affiliations: Industrial Technology Research Institute (ITRI), Taiwan…”

Section: Additional Literaturementioning

confidence: 99%

Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report

Ignatov¹,

Chiang²,

Kuo³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

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 102megapixel 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.

show abstract

“…• Learned End-to-End ISP: [20,24] • Perceptual Image Enhancement: [23,17] • Image Super-Resolution: [23,34,4,41] • Bokeh Effect Rendering: [15,22] • Image Denoising: [1,2] A. Teams and Affiliations Mobile AI 2021 Team Title: Mobile AI 2021 Challenge on Fast and Accurate Quantized Camera Scene Detection on Smartphones Members: Andrey Ignatov 1,2 (andrey@vision.ee.ethz.ch), Grigory Malivenko (grigory.malivenko@gmail.com), Radu Timofte 1,2 (radu.timofte@vision.ee.ethz.ch) Affiliations:…”

Section: Additional Literaturementioning

confidence: 99%

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

Ignatov¹,

Malivenko²,

Timofte³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

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 participants were provided with a large-scale CamSDD dataset consisting of more than 11K images belonging to the 30 most important scene categories. The runtime of all models was evaluated on the popular Apple Bionic A11 platform that can be found in many iOS devices. The proposed solutions are fully compatible with all major mobile AI accelerators and can demonstrate more than 100-200 FPS on the majority of recent smartphone platforms while achieving a top-3 accuracy of more than 98%. A detailed description of all models developed in the challenge is provided in this paper.

show abstract

AIM 2020 Challenge on Rendering Realistic Bokeh

Cited by 38 publications

References 28 publications

Portraiture, Surveillance, and the Continuity Aesthetic of Blur

Portraiture, Surveillance, and the Continuity Aesthetic of Blur

Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report

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

Contact Info

Product

Resources

About