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

Fuoli, Dario; Huang, Zhiwu; Gu, Shuhang; Timofte, Radu; Raventos, Arnau; Esfandiari, Aryan; Karout, Salah; Xu, Xuan; Li, Xin; Xiong, Xin; Wang, Jinge; Michelini, Pablo Navarrete; Zhang, Wenhao; Zhang, Dongyang; Zhu, Hanwei; Xia, Dan; Chen, Haoyu; Gu, Jinjin; Zhang, Zhi; Zhao, Tongtong; Zhao, Shanshan; Akita, Kazutoshi; Ukita, Norimichi; Hrishikesh, P. S.; Puthussery, Densen; Jiji, C. V.

doi:10.1007/978-3-030-66823-5_4

Cited by 30 publications

(14 citation statements)

References 50 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vid3oC [24] is a small dataset consisting of 50 roughly-aligned videos for training and 16 videos for validation recorded with 3 different cameras (a ZED stereo camera, a Canon 5D Mark IV, and a Huawei P20) on a calibrated camera rig. This dataset can be publicly downloaded and has been used in challenges for video super-resolution [7,9] and video quality mapping [8]. Following the setup of [8], we use the videos taken by the ZED (low-quality i.e., source) and Canon (highquality i.e., target) cameras for the video enhancement evaluation.…”

Section: Datasetsmentioning

confidence: 99%

An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement

Fuoli¹,

Huang²,

Paudel³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Video enhancement is a challenging problem, more than that of stills, mainly due to high computational cost, larger data volumes and the difficulty of achieving consistency in the spatio-temporal domain. In practice, these challenges are often coupled with the lack of example pairs, which inhibits the application of supervised learning strategies. To address these challenges, we propose an efficient adversarial video enhancement framework that learns directly from unpaired video examples. In particular, our framework introduces new recurrent cells that consist of interleaved local and global modules for implicit integration of spatial and temporal information. The proposed design allows our recurrent cells to efficiently propagate spatio-temporal information across frames and reduces the need for high complexity networks. Our setting enables learning from unpaired videos in a cyclic adversarial manner, where the proposed recurrent units are employed in all architectures. Efficient training is accomplished by introducing one single discriminator that learns the joint distribution of source and target domain simultaneously. The enhancement results demonstrate clear superiority of the proposed video enhancer over the state-of-theart methods, in all terms of visual quality, quantitative metrics, and inference speed. Notably, our video enhancer is capable of enhancing over 35 frames per second of FullHD video (1080x1920).

show abstract

Section: Datasetsmentioning

confidence: 99%

An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement

Fuoli¹,

Huang²,

Paudel³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This challenge is one of the AIM 2020 associated challenges on: scene relighting and illumination estimation [8], image extreme inpainting [31], learned image signal processing pipeline [15], rendering realistic bokeh [16], real image super-resolution [37], efficient super-resolution [42], and video extreme superresolution [9]. Our development phase has started on May 1st, and the test phase is opened on July 10th.…”

Section: Aim 2020 Vtsr Challengementioning

confidence: 99%

AIM 2020 Challenge on Video Temporal Super-Resolution

Son¹,

Lee²,

Nah³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Videos in the real-world contain various dynamics and motions that may look unnaturally discontinuous in time when the recorded frame rate is low. 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. From low-framerate (15 fps) videos, the challenge participants are required to submit higher-frame-rate (30 and 60 fps) sequences by estimating temporally intermediate frames. 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. There have been 68 registered participants in the competition, and 5 teams (one withdrawn) have competed in the final testing phase. The winning team proposes the enhanced quadratic video interpolation method and achieves state-of-the-art on the VTSR task.

show abstract

“…This challenge is one of the AIM 2020 associated challenges on: scene relighting and illumination estimation [9], image extreme inpainting [33], learned image signal processing pipeline [22], rendering realistic bokeh [23], real image super-resolution [41], efficient super-resolution [42], video temporal superresolution [36] and video extreme super-resolution [10].…”

Section: Introductionmentioning

confidence: 99%

AIM 2020 Challenge on Learned Image Signal Processing Pipeline

Ignatov

Timofte

Zhang

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original low-quality RAW images captured by the Huawei P20 device to the same photos obtained with the Canon 5D DSLR camera. The considered task embraced a number of complex computer vision subtasks, such as image demosaicing, denoising, white balancing, color and contrast correction, demoireing, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions' perceptual results measured in a user study. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical image signal processing pipeline modeling. * A. Ignatov and R. Timofte ({andrey,radu.timofte}@vision.ee.ethz.ch, ETH Zurich) are the challenge organizers, while the other authors participated in the challenge. The Appendix A contains the authors' teams and affiliations. AIM 2020 webpage: https://data.vision.ee.ethz.ch/cvl/aim20/

show abstract

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

Abstract: , Zhiwu Huang, Shuhang Gu and Radu Timofte are the AIM 2020 challenge organizers. http://www.vision.ee.ethz.ch/aim20/ 3 Participants in the challenge. Appendix A contains the authors' teams and affiliations.

Cited by 30 publications

References 50 publications

An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement

An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement

AIM 2020 Challenge on Video Temporal Super-Resolution

AIM 2020 Challenge on Learned Image Signal Processing Pipeline

Contact Info

Product

Resources

About