Filters








37 Hits in 3.1 sec

AIM 2020 Challenge on Rendering Realistic Bokeh [article]

Andrey Ignatov, Radu Timofte, Ming Qian, Congyu Qiao, Jiamin Lin, Zhenyu Guo, Chenghua Li, Cong Leng, Jian Cheng, Juewen Peng, Xianrui Luo, Ke Xian (+23 others)
2020 arXiv   pre-print
This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results.  ...  The participants had to render bokeh effect based on only one single frame without any additional data from other cameras or sensors.  ...  Acknowledgments We thank the AIM 2020 sponsors: Huawei, MediaTek, Qualcomm, NVIDIA, Google and Computer Vision Lab / ETH Zürich.  ... 
arXiv:2011.04988v1 fatcat:taj54kntdbbmfpekn7cz6eqcqe

BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokeh [article]

Ming Qian, Congyu Qiao, Jiamin Lin, Zhenyu Guo, Chenghua Li, Cong Leng, Jian Cheng
2020 arXiv   pre-print
This approach ranked First in AIM 2020 Rendering Realistic Bokeh Challenge Track 1 & Track 2.  ...  Meanwhile, the GAN-based method and perceptual loss are combined for rendering a realistic bokeh effect in the stage of finetuning the model.  ...  dataset [8] was released by AIM 2020 Bokeh Effect Rendering Challenge.  ... 
arXiv:2011.02242v1 fatcat:eygyth566bdsbbbvoufj7xu4zy

Depth-aware Blending of Smoothed Images for Bokeh Effect Generation [article]

Saikat Dutta
2020 arXiv   pre-print
The proposed approach is compared against a saliency detection based baseline and a number of approaches proposed in AIM 2019 Challenge on Bokeh Effect Synthesis.  ...  This approach ranked second in AIM 2019 Bokeh effect challenge-Perceptual Track.  ...  AIM 2019 Challenge on Bokeh Effect Synthesis The proposed solution participated in AIM 2019 Challenge on Bokeh Effect Synthesis which is a competition on example- PSNR ↑ SSIM ↑ LPIPS ↓ Phase Efficiency  ... 
arXiv:2005.14214v1 fatcat:v6ktxifqi5f7poh5jv24tcst4i

Portraiture, Surveillance, and the Continuity Aesthetic of Blur

Stefka Hristova
2021 Frames Cinema Journal  
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  ...  A study on generating realistic bokeh notes specifically why selfies are a good candidate for training the algorithm to recognize human/data subjects.  ... 
doi:10.15664/fcj.v18i1.2249 fatcat:c6a3pqkgoncl3dr23ec7fukxui

AcED: Accurate and Edge-consistent Monocular Depth Estimation [article]

Kunal Swami, Prasanna Vishnu Bondada, Pankaj Kumar Bajpai
2020 arXiv   pre-print
Additionally, we demonstrate practical utility of the proposed method for single camera bokeh solution using in-house dataset of challenging real-life images.  ...  Extensive evaluation of the proposed model on challenging benchmarks reveals its superiority over recent state-of-the-art methods, both quantitatively and qualitatively.  ...  The depth maps generated by AcED on real life images were combined with our human segmentation mask [1] to apply realistic bokeh effect with varying background blur.  ... 
arXiv:2006.09243v1 fatcat:z2rk66hhbbb47mvf5ptwmrkyme

Defocus Blur Detection via Salient Region Detection Prior [article]

Ming Qian and Min Xia and Chunyi Sun and Zhiwei Wang and Liguo Weng
2020 arXiv   pre-print
In an image with bokeh effect, it is obvious that the salient region and the depth-of-field area overlap in most cases.  ...  Defocus blur Detection aims to separate the out-of-focus and depth-of-field areas in photos, which is an important work in computer vision.  ...  DBD is an essential work for many computer vision tasks, as it has latent relationships with several tasks, such as salient region detection [35] , rendering realistic bokeh [34] , quality assessment  ... 
arXiv:2011.09677v1 fatcat:gzexisrkarbenlw273igw26ehm

DriverGym: Democratising Reinforcement Learning for Autonomous Driving [article]

Parth Kothari, Christian Perone, Luca Bergamini, Alexandre Alahi, Peter Ondruska
2021 arXiv   pre-print
Despite promising progress in reinforcement learning (RL), developing algorithms for autonomous driving (AD) remains challenging: one of the critical issues being the absence of an open-source platform  ...  capable of training and effectively validating the RL policies on real-world data.  ...  We would like to thank everyone at Level 5 working on data-driven planning, in particular Sergey Zagoruyko, Alborz Alavian, Oliver Scheel, Yawei Ye, Moritz Niendorf, Stefano Pini and Maciej Wołczyk.  ... 
arXiv:2111.06889v1 fatcat:t2yzmmb2fvd2lj4p4e77iakn54

AIM 2020 Challenge on Video Temporal Super-Resolution [article]

Sanghyun Son, Jaerin Lee, Seungjun Nah, Radu Timofte, Kyoung Mu Lee
2020 arXiv   pre-print
This paper reports the second AIM challenge on Video Temporal Super-Resolution (VTSR), a.k.a. frame interpolation, with a focus on the proposed solutions, results, and analysis.  ...  To simulate realistic and challenging dynamics in the real-world, we employ the REDS_VTSR dataset derived from diverse videos captured in a hand-held camera for training and evaluation purposes.  ...  Acknowledgments We thank all AIM 2020 sponsors: Huawei Technologies Co. Ltd., MediaTek Inc., NVIDIA Corp., Qualcomm Inc., Google, LLC and CVL, ETH Zürich.  ... 
arXiv:2009.12987v1 fatcat:23cngd3i25bupb5lwszpzxthte

AIM 2020 Challenge on Learned Image Signal Processing Pipeline [article]

Andrey Ignatov, Radu Timofte, Zhilu Zhang, Ming Liu, Haolin Wang, Wangmeng Zuo, Jiawei Zhang, Ruimao Zhang, Zhanglin Peng, Sijie Ren, Linhui Dai, Xiaohong Liu (+27 others)
2020 arXiv   pre-print
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results.  ...  The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions' perceptual results measured in a user study.  ...  Acknowledgments We thank the AIM 2020 sponsors: Huawei, MediaTek, Qualcomm, NVIDIA, Google and Computer Vision Lab / ETH Zürich.  ... 
arXiv:2011.04994v1 fatcat:i43uj46xxfhcxgsg7e7l6qbvqe

Review of light field technologies

Shuyao Zhou, Tianqian Zhu, Kanle Shi, Yazi Li, Wen Zheng, Junhai Yong
2021 Visual Computing for Industry, Biomedicine, and Art  
According to these achievements and challenges, in the near future, the applications of light fields could offer more portability, accessibility, compatibility, and ability to visualize the world.  ...  State-of-the-art research has focused on light field acquisition, manipulation, and display. In addition, the research has extended from the laboratory to industry.  ...  [62] proposed a light field refocusing method to improve bokeh rendering and image quality. They first estimated the disparity map and rendered the bokeh on the center-view sub-image.  ... 
doi:10.1186/s42492-021-00096-8 pmid:34862574 pmcid:PMC8642475 fatcat:6rq5rx5svrcerdr7rciaijy3k4

AIM 2020: Scene Relighting and Illumination Estimation Challenge [article]

Majed El Helou, Ruofan Zhou, Sabine Süsstrunk, Radu Timofte, Mahmoud Afifi, Michael S. Brown, Kele Xu, Hengxing Cai, Yuzhong Liu, Li-Wen Wang, Zhi-Song Liu, Chu-Tak Li (+25 others)
2020 arXiv   pre-print
We review the AIM 2020 challenge on virtual image relighting and illumination estimation.  ...  This paper presents the novel VIDIT dataset used in the challenge and the different proposed solutions and final evaluation results over the 3 challenge tracks.  ...  Acknowledgements We thank all AIM 2020 sponsors: Huawei, MediaTek, NVIDIA, Qualcomm, Google and CVL, ETH Zurich (https://data.vision.ee.ethz.ch/cvl/aim20/).  ... 
arXiv:2009.12798v1 fatcat:lkc46rz3trak5d277vzern2saq

Real-time single image depth perception in the wild with handheld devices [article]

Filippo Aleotti, Giulio Zaccaroni, Luca Bartolomei, Matteo Poggi, Fabio Tosi, Stefano Mattoccia
2020 arXiv   pre-print
For the latter, depth estimation from a single image represents the most versatile solution, since a standard camera is available on almost any handheld device.  ...  in this paper, we deeply investigate these issues showing how they are both addressable adopting appropriate network design and training strategies -- also outlining how to map the resulting networks on  ...  The first application consists of a bokeh filter, aimed at blurring an image according to the distance from the camera.  ... 
arXiv:2006.05724v1 fatcat:llf5ld6tcnd3fgtqfnetsoh4gq

AIM 2020 Challenge on Image Extreme Inpainting [article]

Evangelos Ntavelis, Andrés Romero, Siavash Bigdeli, Radu Timofte
2020 arXiv   pre-print
This paper reviews the AIM 2020 challenge on extreme image inpainting.  ...  The challenge had 88 and 74 participants, respectively. 11 and 6 teams competed in the final phase of the challenge, respectively.  ...  Acknowledgements We thank the AIM 2020 sponsors: Huawei, MediaTek, Qualcomm AI Research, NVIDIA, Google and Computer Vision Lab / ETH Zürich.  ... 
arXiv:2010.01110v1 fatcat:sple2mqkkzh2nfz527vqr6c3oi

AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results [article]

Dario Fuoli, Zhiwu Huang, Shuhang Gu, Radu Timofte, Arnau Raventos, Aryan Esfandiari, Salah Karout, Xuan Xu, Xin Li, Xin Xiong, Jinge Wang, Pablo Navarrete Michelini (+14 others)
2020 arXiv   pre-print
This paper reviews the video extreme super-resolution challenge associated with the AIM 2020 workshop at ECCV 2020.  ...  Track 2 therefore aims at generating visually pleasing results, which are ranked according to human perception, evaluated by a user study.  ...  Acknowledgements We thank the AIM 2020 sponsors: Huawei, MediaTek, NVIDIA, Qualcomm, Google, and Computer Vision Lab (CVL), ETH Zurich.  ... 
arXiv:2009.06290v1 fatcat:bbgfzmwupfgcnigwr2onun4zzm

Portrait Quality Assessment using Multi-Scale CNN

Chahine Nicolas, Belkarfa Salim
2021 London Imaging Meeting  
To this aim, we create a realistic mannequins database, which contains images from different cameras, shot in several lighting conditions.  ...  In this paper, we propose a novel and standardized approach to the problem of camera-quality assessment on portrait scenes.  ...  For portrait images, the main focus is to evaluate the render quality of the face. On this matter, characteristics like skin tone, bokeh, texture details and skin smoothness are mostly of interest.  ... 
doi:10.2352/issn.2694-118x.2021.lim-5 fatcat:n2qvpdfotbhf5dnahla7jj7gpu
« Previous Showing results 1 — 15 out of 37 results