NTIRE: 3rd New Trends in Image Restoration and Enhancement workshop and challenges on image super-resolution, dehazing and spectral reconstruction 2018
In conjunction with CVPR 2018

Website: http://www.vision.ee.ethz.ch/ntire18/
Contact: radu.timofte [at] vision.ee.ethz.ch

Scope

Image restoration and image enhancement are key computer vision tasks, aiming at the restoration of degraded image content or the filling in of missing information. Recent years have witnessed an increased interest from the vision and graphics communities in these fundamental topics of research. Not only has there been a constantly growing flow of related papers, but also substantial progress has been achieved.

Each step forward eases the use of images by people or computers for the fulfillment of further tasks, with image restoration or enhancement serving as an important frontend. Not surprisingly then, there is an ever growing range of applications in fields such as surveillance, the automotive industry, electronics, remote sensing, or medical image analysis. The emergence and ubiquitous use of mobile and wearable devices offer another fertile ground for additional applications and faster methods.

This workshop aims to provide an overview of the new trends and advances in those areas. Moreover, it will offer an opportunity for academic and industrial attendees to interact and explore collaborations.


Topics

Papers addressing topics related to image/video restoration and enhancement are invited. The topics include, but are not limited to:

● Image/video inpainting
● Image/video deblurring
● Image/video denoising
● Image/video upsampling and super-resolution
● Image/video filtering
● Image/video dehazing
● Demosaicing
● Image/video compression
● Artifact removal
● Image enhancement: brightening, color adjustment, sharpening, etc.
● Style transfer
● Image/video generation and image hallucination
● Image/video quality assessment
● Hyperspectral imaging
● Underwater imaging
● Aerial and satellite imaging
● Methods robust to changing weather conditions / adverse outdoor conditions
● Studies and applications of the above.

Submission

A paper submission has to be in English, in pdf format, and at most 8 pages (excluding references) in CVPR style. The paper format must follow the same guidelines as for all CVPR submissions.
http://cvpr2018.thecvf.com/submission/main_conference/author_guidelines
The review process is double blind. Authors do not know the names of the chair/reviewers of their papers. Reviewers do not know the names of the authors.
Dual submission is allowed with CVPR main conference only. If a paper is submitted also to CVPR and accepted, the paper cannot be published both at the CVPR and the workshop.

For the paper submissions, please go to the online submission site
https://cmt3.research.microsoft.com/NTIRE2018

Accepted and presented papers will be published after the conference in the CVPR Workshops Proceedings on by IEEE (http://www.ieee.org) and Computer Vision Foundation (www.cv-foundation.org).

The author kit provides a LaTeX2e template for paper submissions. Please refer to the example for detailed formatting instructions. If you use a different document processing system then see the CVPR author instruction page.

Author Kit: http://cvpr2018.thecvf.com/files/cvpr2018AuthorKit.zip

Workshop Dates

● Submission Deadline: March 22, 2018 (extended!!)
● Decisions: April 12, 2018
● Camera Ready Deadline: April 19, 2018


NTIRE 2018 Challenge on Image Super-Resolution (ongoing!)

GOAL: to gauge the current state-of-the-art in (example-based) single-image super-resolution under realistic conditions, to compare and to promote different solutions

TRACKS: 4 tracks using classic and realistic degradation operators and a large dataset


NTIRE 2018 Challenge on Image Dehazing (ongoing!)

GOAL: to gauge the current state-of-the-art in image dehazing for real haze, to compare and to promote different solutions we are organizing an NTIRE challenge in conjunction with the CVPR 2018 conference. A novel dataset of real hazy images with ground truth will be introduced with the challenge. It is the first image dehazing online challenge.

TRACKS: 2 tracks for indoor and outdoor dehazing


NTIRE 2018 Challenge on Spectral Reconstruction from RGB images (ongoing!)

GOAL: to gauge the current state-of-the-art in spectral reconstruction from RGB images, to compare and to promote different solutions we are organizing an NTIRE challenge in conjunction with the CVPR 2018 conference. The largest dataset to date will be introduced with the challenge. It is the first spectral reconstruction from RGB images online challenge.

TRACKS: 2 tracks for ideal and realistic conditions


PARTICIPATION

To learn more about the ONGOING challenges and to participate:
http://www.vision.ee.ethz.ch/ntire18/


Challenges Dates

● Release of train data: January 10, 2018
● Validation server online: January 15, 2018
● Competitions end: March 22, 2018 (extended!)


Organizers

● Radu Timofte, ETH Zurich, Switzerland
● Ming-Hsuan Yang, University of California at Merced, US
● Shuhang Gu, ETH Zurich, Switzerland
● Jiqing Wu, ETH Zurich, Switzerland
● Lei Zhang, The Hong Kong Polytechnic University
● Luc Van Gool, KU Leuven, Belgium and ETH Zurich, Switzerland
● Cosmin Ancuti, Université catholique de Louvain (UCL), Belgium
● Codruta O. Ancuti, University Politehnica Timisoara, Romania
● Boaz Arad, Ben-Gurion University, Israel
● Ohad Ben-Shahar, Ben-Gurion University, Israel



Program Committee (to be updated)


Cosmin Ancuti, Université catholique de Louvain (UCL), Belgium
Nick Barnes, Data61, Australia
Michael S. Brown, York University, Canada
Subhasis Chaudhuri, IIT Bombay, India
Sunghyun Cho, Samsung
Chao Dong, SenseTime
Weisheng Dong, Xidian University, China
Alexey Dosovitskiy, Intel Labs
Touradj Ebrahimi, EPFL, Switzerland
Michael Elad, Technion, Israel
Corneliu Florea, University Politehnica of Bucharest, Romania
Alessandro Foi, Tampere University of Technology, Finland
Peter Gehler, University of Tübingen, MPI Intelligent Systems, Amazon, Germany
Bastian Goldluecke, University of Konstanz, Germany
Luc Van Gool, ETH Zürich and KU Leuven, Belgium
Shuhang Gu, ETH Zürich, Switzerland
Michael Hirsch, Amazon
Hiroto Honda, DeNA Co., Japan
Jia-Bin Huang, Virginia Tech, US
Michal Irani, Weizmann Institute, Israel
Phillip Isola, UC Berkeley, US
Zhe Hu, Light.co
Sing Bing Kang, Microsoft Research, US
Jan Kautz, NVIDIA Research, US
Seon Joo Kim, Yonsei University, Korea
Vivek Kwatra, Google
In So Kweon, KAIST, Korea
Christian Ledig, Twitter Inc.
Kyoung Mu Lee, Seoul National University, South Korea
Seungyong Lee, POSTECH, South Korea
Stephen Lin, Microsoft Research Asia
Chen Change Loy, Chinese University of Hong Kong
Vladimir Lukin, National Aerospace University, Ukraine
Kai-Kuang Ma, Nanyang Technological University, Singapore
Vasile Manta, Technical University of Iasi, Romania
Yasuyuki Matsushita, Osaka University, Japan
Peyman Milanfar, Google and UCSC, US
Rafael Molina Soriano, University of Granada, Spain
Yusuke Monno, Tokyo Institute of Technology, Japan
Hajime Nagahara, Osaka University, Japan
Vinay P. Namboodiri, IIT Kanpur, India
Sebastian Nowozin, Microsoft Research Cambridge, UK
Federico Perazzi, Disney Research
Aleksandra Pizurica, Ghent University, Belgium
Sylvain Paris, Adobe
Fatih Porikli, Australian National University, NICTA, Australia
Hayder Radha, Michigan State University, US
Tobias Ritschel, University College London, UK
Antonio Robles-Kelly, CSIRO, Australia
Stefan Roth, TU Darmstadt, Germany
Aline Roumy, INRIA, France
Jordi Salvador, Amazon, US
Yoichi Sato, University of Tokyo, Japan
Konrad Schindler, ETH Zurich, Switzerland
Samuel Schulter, NEC Labs America
Nicu Sebe, University of Trento, Italy
Eli Shechtman, Adobe Research, US
Boxin Shi, National Institute of Advanced Industrial Science and Technology (AIST), Japan
Wenzhe Shi, Twitter Inc.
Alexander Sorkine-Hornung, Disney Research
Sabine Süsstrunk, EPFL, Switzerland
Yu-Wing Tai, Tencent Youtu
Hugues Talbot, Université Paris Est, France
Robby T. Tan, Yale-NUS College, Singapore
Masayuki Tanaka, Tokyo Institute of Technology, Japan
Jean-Philippe Tarel, IFSTTAR, France
Radu Timofte, ETH Zürich, Switzerland
George Toderici, Google, US
Ashok Veeraraghavan, Rice University, US
Jue Wang, Megvii Research, US
Chih-Yuan Yang, UC Merced, US
Jianchao Yang, Snapchat
Ming-Hsuan Yang, University of California at Merced, US
Qingxiong Yang, Didi Chuxing, China
Jong Chul Ye, KAIST, Korea
Jason Yosinski, Uber AI Labs, US
Wenjun Zeng, Microsoft Research
Lei Zhang, The Hong Kong Polytechnic University
Wangmeng Zuo, Harbin Institute of Technology, China


Speakers

Xian-Sheng Hua (Alibaba)
Ming-Yu Liu (NVIDIA)
Graham Finlayson (University of East Anglia, Spectral Edge Ltd, Simon Fraser University)
Liang Lin (SenseTime, Sun Yat-sen University)
William T. Freeman (MIT/Google)


Sponsors

Alibaba
NVIDIA
SenseTime
CodeOcean
Huawei
Google
Disney Research
Amazon


Contact

Email: radu.timofte [at] vision.ee.ethz.ch
Website: http://www.vision.ee.ethz.ch/ntire18/