NTIRE 2020 Image Deblurring Challenge - Track 2 on Smartphone

Organized by Radu - Current server time: Jan. 18, 2020, 9:44 a.m. UTC


Dec. 27, 2019, 11:59 p.m. UTC


March 16, 2020, midnight UTC


Competition Ends
March 23, 2020, 11:59 p.m. UTC

NTIRE workshop and challenge on image deblurring @ CVPR 2020


Single-Image Deblurring Challenge on Mobile devices


Important dates

  • 2019.12.27 Release of train and validation data (input and target images)
  • 2020.01.12 Validation server online (CodaLab, every 10th frame)
  • 2020.03.16 Final phase begins, test data release (only input images), validation server closed
  • 2020.03.23 Test output results submission deadline (CodaLab, every 10th frame)
  • 2020.03.24 Fact sheets submission deadline
  • 2020.03.24 Code submission deadline
  • 2020.03.24 Full test results submission deadline (via email, all results)
  • 2020.03.26 Preliminary test results release to the participants
  • 2020.04.04 Paper submission deadline for entries from the challenge
  • 2020.06.15 NTIRE workshop and challenges, results and award ceremony (CVPR 2020, Seattle, US)


Challenge overview

The 5th edition of NTIRE: New Trends in Image Restoration and Enhancement workshop will be held June 15, 2020 in conjunction with CVPR 2020 in Seattle, US.

Image manipulation is a key computer vision tasks, aiming at the restoration of degraded image content, the filling in of missing information, or the needed transformation and/or manipulation to achieve the desired target (with respect to perceptual quality, contents, or performance of apps working on such images). 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, as image manipulation serves 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, etc. 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.

Jointly with NTIRE workshop, we have an NTIRE challenge on example-based Image Deblurring, that is, the task of restoring the contents in a blurry input image based on a set of prior examples of clean and blurry images. The aim of the challenge is to obtain a solution capable to produce deblurring results with the best fidelity (PSNR) to the ground truth.



The top-ranked participants will be awarded and invited to follow the CVPR submission guide for workshops to describe their solution and to submit to the associated NTIRE workshop at CVPR 2020.

More details are found in the data section of the competition.


To learn more about each competition, to participate in the challenge, and to access the new dataset everybody is invited to register.

The training data is already made available to the registered participants.

Provided Resources

  • Scripts: With the dataset, the organizers will provide scripts to facilitate the reproducibility of the images and performance evaluation results. More information is provided on the data page.
  • Contact: You can use the forum on the data description page (highly recommended!) or directly contact the challenge organizers by email ( Seungjun Nah (seungjun.nah [at] gmail.com), Sanghyun Son (thstkdgus35 [at] snu.ac.kr) and Radu Timofte (Radu.Timofte [at] vision.ee.ethz.ch)) if you have doubts or any question.

NTIRE workshop and challenge on image deblurring @ CVPR 2020


Single-Image Deblurring Challenge on Mobile devices



We evaluate the single-image deblurring result by comparing it with the ground truth video frames.

The final goal of this challenge is to generate a sharp image from a given blurry image input using the mobile device. By removing the motion blurs, sharp and visually clear images are generated. During the testing phase, challenge participants will submit the deblurred images.

To measure the fidelity, we use the standard Peak Signal to Noise Ratio (PSNR) and, complementarily, the Structural Similarity (SSIM) index as they are often employed in the literature. PSNR and SSIM implementations are found in most of the image processing toolboxes. We report the average results over all the processed frames belonging to the evaluation dataset.

At the same time, final scores will also consider how fast each model can be executed on the real Android device. Therefore, it is crucial to optimize your model in efficient ways and accelerate them. We also note that the submitted model would not consume more than 4GB memory due to the limited resource in the mobile environment. As it requires more time to optimize our evaluation framework, we will update the detailed evaluation criterion soon. Currently, we are expecting the following scheme:

Score = PSNR + MAX(FPS / const_a, const_b).

The provided dataset, REDS is generated from original videos captured at 120 fps. To generate a blurry image, a sequence of the captured frames are averaged with additional processes. The motion blur is made to be temporally smooth and realistic.

Due to the submission size limit of CodaLab, the submission is to be made on another website. (link TBA) During the development phase, the participants will make their own evaluation with the validation set. We recommend not using the validation set for training purposes. During the testing phase, the participants will submit the whole restoration results of the test set.


To submit the results, participants should follow the rules:

  1. The processed output images should be named by the corresponding sequence number and frame number that is consistent with the provided inputs. For example, 0th frame from sequence 000 is "000_00000000.png", and the 58th frame from sequence 013 is "013_00000058.png".
  2. Create a ZIP archive containing all the output images. The ZIP archive should also contain a readme.txt file. Note that the archive should not include folders and all the frames/files should be in the root of the archive.
  3. The readme.txt file should contain the following lines filled in with the runtime per image (in seconds) of the solution, 1 or 0 accordingly if employs CPU or GPU at runtime, and 1 or 0 if employs extra data for training the models or not.
    runtime per image [s] : 10.43
    CPU[1] / GPU[0] : 1
    Extra Data [1] / No Extra Data [0] : 1
    Other description : Solution based on A+ of Timofte et al. ACCV 2014. We have a Matlab/C++ implementation, and report single core CPU runtime. The method was trained on Train 91 of Yang et al. and BSDS 200 of the Berkeley segmentation dataset. 
     The last part of the file can have any description you want about the code producing the provided results (dependencies, link, scripts, etc.)
    The provided information is very important both during the validation period when different teams can compare their results/solutions but also for establishing the final ranking of the teams and their methods.

After the testing phase, the participants will submit the factsheet and source code to all of the challenge organizers: Submission account (TBA), Seungjun Nah (seungjun.nah [at] gmail.com), Sanghyun Son (thstkdgus35 [at] snu.ac.kr) and Radu Timofte (Radu.Timofte [at] vision.ee.ethz.ch) by email. The final submission should be made by the following rules:

  1. The submitted fact sheet/code must be from the same method that generated the last submission to the CodaLab. We will check the consistency with the submitted results. Otherwise, the submission is void.
  2. Either the source code or executable must be submitted, too. Reproducibility is a necessary condition.
  3. Factsheet describing the method details should be submitted together. The factsheet format is provided with data. Participants must submit a compiled pdf file. We encourage participants to provide details and enclose latex and figure image sources together. This helps writing the challenge summary report.

NTIRE workshop and challenge on image deblurring @ CVPR 2020


Single-Image Deblurring Challenge on Mobile devices

These are the official rules (terms and conditions) that govern how the NTIRE challenge on example-based image deblurring 2020 will operate. This challenge will be simply referred to as the "challenge" or the "contest" throughout the remaining part of these rules and may be named as "NTIRE" or "REDS" benchmark, challenge, or contest, elsewhere (our webpage, our documentation, other publications).

In these rules, "we", "our", and "us" refer to the organizers (Seungjun Nah (seungjun.nah [at] gmail.com), Sanghyun Son (thstkdgus35 [at] snu.ac.kr) and Radu Timofte (Radu.Timofte [at] vision.ee.ethz.ch)) of NTIRE challenge and "you" and "yourself" refer to an eligible contest participant.

Note that these official rules can change during the contest until the start of the final phase. If at any point during the contest the registered participant considers that can not anymore meet the eligibility criteria or does not agree with the changes in the official terms and conditions then it is the responsibility of the participant to send an email to the organizers such that to be removed from all the records. Once the contest is over no change is possible in the status of the registered participants and their entries.

1. Contest description

This is a skill-based contest and chance plays no part in the determination of the winner (s).

The goal of the contest is to restore the clean contents in a blurry input video and the challenge is called video deblurring.

Focus of the contest: it will be made available REDS dataset adapted for the specific needs of the challenge. The images have a large diversity of contents. We will refer to this dataset, its partition, and related materials as REDS. The dataset is divided into training, validation and testing data. The aim is to achieve deblurred output videos with the highest fidelity (PSNR) to the ground truth. The participants will not have access to the ground truth images from the test data. The ranking of the participants is according to the performance of their methods on the test data. The participants will provide descriptions of their methods, details on (run)time complexity, platform and (extra) data used for modeling. The winners will be determined according to their entries, the reproducibility of the results and uploaded codes or executables, and the above mentioned criteria as judged by the organizers.

2. Tentative contest schedule

The registered participants will be notified by email if any changes are made to the schedule. The schedule is available on the NTIRE workshop web page and on the Overview of the Codalab competition.

3. Eligibility

You are eligible to register and compete in this contest only if you meet all the following requirements:

  • you are an individual or a team of people willing to contribute to the open tasks, who accepts to follow the rules of this contest
  • you are not an NTIRE challenge organizer or an employee of NTIRE challenge organizers
  • you are not involved in any part of the administration and execution of this contest
  • you are not a first-degree relative, partner, household member of an employee or of an organizer of NTIRE challenge or of a person involved in any part of the administration and execution of this contest

This contest is void wherever it is prohibited by law.

Entries submitted but not qualified to enter the contest, it is considered voluntary and for any entry you submit, NTIRE reserves the right to evaluate it for scientific purposes, however, under no circumstances will such entries qualify for sponsored prizes. If you are an employee, affiliated with or representant of any of the NTIRE challenge sponsors then you are allowed to enter in the contest and get ranked, however, if you will rank among the winners with eligible entries you will receive only a diploma award and none of the sponsored money, products or travel grants.

NOTE: industry and research labs are allowed to submit entries and to compete in both the validation phase and final test phase. However, in order to get officially ranked on the final test leaderboard and to be eligible for awards the reproducibility of the results is a must and, therefore, the participants need to make available and submit their codes or executables. All the top entries will be checked for reproducibility and marked accordingly.

We will have 3 categories of entries in the final test ranking:
1) checked with publicly released codes 
2) checked with publicly released executable
3) unchecked (with or without released codes or executables)


4. Entry

In order to be eligible for judging, an entry must meet all the following requirements:

Entry contents: the participants are required to submit image results and code or executables. To be eligible for prizes, the top-ranking participants should publicly release their code or executables under a license of their choice, taken among popular OSI-approved licenses (http://opensource.org/licenses) and make their code or executables online accessible for a period of not less than one year following the end of the challenge (applies only for top three ranked participants of the competition). To enter the final ranking the participants will need to fill out a survey (fact sheet) briefly describing their method. All the participants are also invited (not mandatory) to submit a paper for peer-reviewing and publication at the NTIRE Workshop and Challenges (to be held on June, 2020, Seattle, US). To be eligible for prizes, the participants' score must improve the baseline performance provided by the challenge organizers.

Use of data provided: all data provided by NTIRE are freely available to the participants from the website of the challenge under license terms provided with the data. The data are available only for open research and educational purposes, within the scope of the challenge. NTIRE and the organizers make no warranties regarding the database, including but not limited to warranties of non-infringement or fitness for a particular purpose. The copyright of the images remains in the property of their respective owners. By downloading and making use of the data, you accept full responsibility for using the data. You shall defend and indemnify NTIRE and the organizers, including their employees, Trustees, officers and agents, against any and all claims arising from your use of the data. You agree not to redistribute the data without this notice.

  • Test data: The organizers will use the test data for the final evaluation and ranking of the entries. The ground truth test data will no be made available to the participants during the contest.
  • Training and validation data: The organizers will make available to the participants a training dataset with ground truth images and a validation dataset without ground truth images. The ground truth images for the validation dataset is released at the start of the final phase when the test data without ground truth images will be made available.
  • Post-challenge analysis: the organizers may also perform additional post-challenge analyses using extra-data, but without effect on the challenge ranking.
  • Submission: the entries will be online submitted via the CodaLab web platform. During the development phase, while the validation server is online, the participants will receive immediate feedback on validation data. The final evaluation will be computed automatically on the test data submissions, but the final scores will be released after the challenge is over.
  • Original work, permissions: In addition, by submitting your entry into this contest you confirm that, to the best of your knowledge: - your entry is your own original work; and - your entry only includes material that you own, or that you have permission to use.

5. Potential use of entry

Other than what is set forth below, we are not claiming any ownership rights to your entry. However, by submitting your entry, you:

Are granting us an irrevocable, worldwide right and license, in exchange for your opportunity to participate in the contest and potential prize awards, for the duration of the protection of the copyrights to:

  1. Use, review, assess, test and otherwise analyze results submitted or produced by your code or executable and other material submitted by you in connection with this contest and any future research or contests by the organizers; and
  2. Feature your entry and all its content in connection with the promotion of this contest in all media (now known or later developed);

Agree to sign any necessary documentation that may be required for us and our designees to make use of the rights you granted above;

Understand and acknowledge that we and other entrants may have developed or commissioned materials similar or identical to your submission and you waive any claims you may have resulting from any similarities to your entry;

Understand that we cannot control the incoming information you will disclose to our representatives or our co-sponsor’s representatives in the course of entering, or what our representatives will remember about your entry. You also understand that we will not restrict work assignments of representatives or our co-sponsor’s representatives who have had access to your entry. By entering this contest, you agree that use of information in our representatives’ or our co-sponsor’s representatives unaided memories in the development or deployment of our products or services does not create liability for us under this agreement or copyright or trade secret law;

Understand that you will not receive any compensation or credit for use of your entry, other than what is described in these official rules.

If you do not want to grant us these rights to your entry, please do not enter this contest.

6. Submission of entries

The participants will follow the instructions on the CodaLab website to submit entries

The participants will be registered as mutually exclusive teams. Each team is allowed to submit only one single final entry. We are not responsible for entries that we do not receive for any reason, or for entries that we receive but do not work properly.

The participants must follow the instructions and the rules. We will automatically disqualify incomplete or invalid entries.

7. Judging the entries

The board of NTIRE will select a panel of judges to judge the entries; all judges will be forbidden to enter the contest and will be experts in causality, statistics, machine learning, computer vision, or a related field, or experts in challenge organization. A list of the judges will be made available upon request. The judges will review all eligible entries received and select three winners for each of the two competition tracks based upon the prediction score on test data. The judges will verify that the winners complied with the rules, including that they documented their method by filling out a fact sheet.

The decisions of these judges are final and binding. The distribution of prizes according to the decisions made by the judges will be made within three (3) months after completion of the last round of the contest. If we do not receive a sufficient number of entries meeting the entry requirements, we may, at our discretion based on the above criteria, not award any or all of the contest prizes below. In the event of a tie between any eligible entries, the tie will be broken by giving preference to the earliest submission, using the time stamp of the submission platform.

8. Prizes and Awards

The financial sponsors of this contest are listed on NTIRE 2020 workshop web page. There will be economic incentive prizes and travel grants for the winners (based on availability) to boost contest participation; these prizes will not require participants to enter into an IP agreement with any of the sponsors, to disclose algorithms, or to deliver source code to them. The participants affiliated with the industry sponsors agree to not receive any sponsored money, product or travel grant in the case they will be among the winners.

Incentive Prizes for each track competitions (tentative, the prizes depend on attracted funds from the sponsors)

  • 1st place: ?00$ + ?GPU + award certificate
  • 2nd place: ?00$ + ?GPU + award certificate
  • 3rd place: ?00$ + award certificate

9. Other Sponsored Events

Publishing papers is optional and will not be a condition for entering the challenge or winning prizes. The top-ranking participants are invited to submit a maximum 8-pages paper (CVPR 2020 author rules) for peer-reviewing to AIM workshop.

The results of the challenge will be published together with NTIRE 2020 workshop papers in the 2020 CVPR Workshops proceedings.

The top-ranked participants and participants contributing interesting and novel methods to the challenge will be invited to be co-authors of the challenge report paper which will be published in the 2020 CVPR Workshops proceedings. A detailed description of the ranked solution as well as the reproducibility of the results are a must to be an eligible co-author.

10. Notifications

If there is any change to data, schedule, instructions of participation, or these rules, the registered participants will be notified at the email they provided with the registration.

Within seven days following the determination of winners, we will send a notification to the potential winners. If the notification that we send is returned as undeliverable, or you are otherwise unreachable for any reason, we may award the prize to an alternate winner, unless forbidden by applicable law.

The prize such as money, product, or travel grant will be delivered to the registered team leader given that the team is not affiliated with any of the sponsors. It's up to the team to share the prize. If this person becomes unavailable for any reason, the prize will be delivered to be the authorized account holder of the e-mail address used to make the winning entry.

If you are a potential winner, we may require you to sign a declaration of eligibility, use, indemnity and liability/publicity release and applicable tax forms. If you are a potential winner and are a minor in your place of residence, and we require that your parent or legal guardian will be designated as the winner, and we may require that they sign a declaration of eligibility, use, indemnity and liability/publicity release on your behalf. If you, (or your parent/legal guardian if applicable), do not sign and return these required forms within the time period listed on the winner notification message, we may disqualify you (or the designated parent/legal guardian) and select an alternate selected winner.


The terms and conditions are inspired by and use verbatim text from the `Terms and conditions' of ChaLearn Looking at People Challenges and of the NTIRE 2017, 2018, and 2019 challenges .

NTIRE workshop and challenge on image deblurring @ CVPR 2020


Single-Image Deblurring Challenge on Mobile devices




The NTIRE challenge on Image Deblurring is organized jointly with the NTIRE 2020 workshop. The results of the challenge will be published at NTIRE 2020 workshop and in the CVPR 2020 Workshops proceedings.


Seungjun Nah (seungjun.nah [at] gmail.com), Sanghyun Son (thstkdgus35 [at] snu.ac.kr) and Radu Timofte (Radu.Timofte [at] vision.ee.ethz.ch) are the contact persons and direct managers of the NTIRE challenge.


More information about NTIRE workshop and challenge organizers is available here: http://www.vision.ee.ethz.ch/ntire20/

NTIRE workshop and challenge on image deblurring @ CVPR 2020


Single-Image Deblurring Challenge on Mobile devices


Please read the attached links carefully to submit executable models. You can also follow the tutorial from the Github for practice.


Submission File 

For fair comparison, we only accept TFLite models (.tflite). Runtime will be measured on the real Android device (Google Pixel 4). For those who are not familiar to TensorFlow and TFLite, we provide simple gudelines for the submission.


Training your model

We highly recommend to train your model with the TensorFlow 2.1 framework, especially with Keras. Once trained, Keras models can be converted to TFLite models easily.


Evaluating the model on your PC

You can use the TFLite interpreter to execute your TFLite model on your PC. The evaluation script can be downloaded from here. (WILL BE INCLUDED SOON)


Evaluating the model on your PC (Android emulation)

Install the Android studio on your PC.  In Ubuntu, follow the below:

$ sudo add-apt-repository ppa:maarten-fonville/android-studio

$ sudo apt-get update

$ sudo apt-get install android-studio

Then, run the Android studio by typing:

$ /opt/android-studio/bin/studio.sh


We will provide more details later.


Evaluating the model on your mobile device

You need to turn the USB debugging mode on your device.


Google Pixel 4 hardware specs

Official website (May not be available in some countries)

OS: Android 10

Chipset: Qualcomm SM8150 Snapdragon 855 (7nm)

CPU: Octa-core (1x2.84 GHz Kryo 485 & 3x2.42 GHz Kryo 485 & 4x1.78 GHz Kryo 485)

GPU: Adreno 640


Storage: Starts from 64GB


In Pixel4, you can execute two types of models (full-precision, quantized) on three hardwares (CPU, GPU, NNAPI). However, the quantized model is not supported on GPU. You can submit and specify any types of model and hardware.


Start: Dec. 27, 2019, 11:59 p.m.


Start: March 16, 2020, midnight

Competition Ends

March 23, 2020, 11:59 p.m.

You must be logged in to participate in competitions.

Sign In
# Username Score
1 SeungjunNah 26.25