The 10th edition of NTIRE: New Trends in Image Restoration and Enhancement workshop will be held in June 2025 in conjunction with CVPR 2025 in Nashville, USA.
Image manipulation is a key computer vision task, aiming at the restoration of degraded image content, the filling in of missing information, or the needed transformation and/or manipulation to achieve a 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 front end. Not surprisingly then, there is an ever-growing range of applications in fields such as surveillance, the automotive industry, electronics, remote sensing, 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.
In collaboration with the NTIRE workshop, we are hosting a challenge focused on Efficient Super-Resolution. This involves the task of enhancing the resolution of an input image by a factor of x4, utilizing a set of pre-existing examples comprising both low-resolution and their corresponding high-resolution images. The challenge encompasses one ๐ main track which consists of three ๐ sub-tracks, i.e., the Inference Runtime, FLOPs (Floating Point Operations Per Second), and Parameters. The baseline method in NTIRE2025_ESR is EFDN (Code) (Wang Yan, 2023), the 1st place for the overall performance of the NTIRE2023 Efficient Super-Resolution Challenge. Details are shown below:
๐ Main-track: Overall Performance (Runtime, Parameters, FLOPs,) The aim is to obtain a network design/solution with the best overall performance in terms of inference runtime, FLOPS, and parameters on a common GPU (i.e., NVIDIA RTX A6000 GPU) while being constrained to maintain or improve the threshold PSNR results.
๐ Sub-track 1: Inference Runtime, the aim is to obtain a network design/solution with the lowest inference time (runtime) on a common GPU (i.e., NVIDIA RTX A6000 GPU) while being constrained to maintain or improve over the baseline method EFDN in terms of number of parameters, FLOPs, and the threshold PSNR result.
๐ Sub-track 2: FLOPs, the aim is to obtain a network design/solution with the lowest amount of FLOPs on a common GPU (i.e., NVIDIA RTX A6000 GPU) while being constrained to maintain or improve the inference runtime, the parameters, and the threshold PSNR results.
๐ Sub-track 3: Parameters, the aim is to obtain a network design/solution with the lowest amount of parameters on a common GPU (i.e., NVIDIA RTX A6000 GPU) while being constrained to maintain the FLOPs, the inference time (runtime), and the threshold PSNR results.
The threshold PSNR is set to 26.90 dB on the DIV2K_LSDIR_valid dataset, and 26.99 dB on the DIV2K_LSDIR_test datasets. It's important to highlight that to determine the final ranking and challenge winners, greater weight will be given to teams or participants who demonstrate improvements in more than one aspect (runtime, FLOPs, and parameters) over the provided reference solution.
To ensure fairness in the evaluation process, it is imperative to adhere to the following guidelines:
Please refer to the following materials for more details:
[1] Ren Bin, et al. "The ninth NTIRE 2024 efficient super-resolution challenge report" CVPR Workshops, 2024
[2] Li, Yawei, et al. "NTIRE 2023 challenge on efficient super-resolution: Methods and results" CVPR Workshops, 2023
[3] Li, Yawei, et al. "NTIRE 2022 challenge on efficient super-resolution: Methods and results" CVPR Workshops, 2022
[4] The test Code: https://github.com/Amazingren/NTIRE2025_ESR
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 2025.
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.
The evaluation consists of the comparison of the x4 super-resolved images with the ground truth images and the reporting of the number of parameters (memory), FLOPs, and inference time/runtime of the solution.
Only deep-learned solutions working with PyTorch are sought. Other solutions will be accepted but will not be officially ranked.
Note that we will rely on a self-reported number of parameters and runtime/inference time in the validation phase, while for the final test phase ranking the challenge organizers will check and run the provided solutions and compute the measures, such as runtime, parameters, and FLOPs.
The entry EFDN_baseline is the baseline created by the organizers based on the 1st place for the overall performance of the NTIRE2023 Efficient SR Challenge (The organizers have generated all reported baseline results using the NVIDIA RTX A6000 GPU. For consistency, it is recommended, though NOT mandatory, that you assess your model on the same GPU type).
For submitting the results, you need to follow these steps:
Runtime per image [s] : 0.01669
Parameters : 276000
FLOPs [G]: 16.70
Extra Data [1] / No Extra Data [0] : 0
Other description : Model name: EFDN_baseline; GPU: NVIDIA RTX A6000
After the organizers receive all the submitted codes/checkpoints/results, four steps are adopted for the evaluation:
Score_Runtime = exp(2*Runtime / Runtime_EFDN)
Score_FLOPs = exp(2*FLOPs / FLOPs_EFDN)
Score_Params = exp(2*Params / Params_EFDN)
Score_Final = 0.7*Score_Runtime + 0.15*Score_FLOPs + 0.15*Score_Params
Let's take the baseline as an example, given the results (i.e., average Runtime_EFDN = 16.69 ms, FLOPs_EFDN = 16.70 G, and Params_EFDN = 0.276 M) of EFDN, we have:
Score_Runtime = 7.3819
Score_FLOPs = 7.3819
Score_Params = 7.3819
Score_Final = 7.3819
โ The ranking for each sub-track ๐ will be generated based on the corresponding Scores (i.e., Score_Runtime, Score_FLOPs, and Score_Params), while for the main track ๐ , the ranking will be determined by the Score_Final. For all the scores, the lower the better.
These are the official rules (terms and conditions) that govern how the NTIRE challenge on efficient super-resolution 2025 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 the "NTIRE" benchmark, challenge, or contest, elsewhere (our webpage, our documentation, other publications).
In these rules, "we", "our", and "us" refer to the organizers (Yawei Li <yawei.li@vision.ee.ethz.ch>, Bin Ren <bin.ren@unitn.it>, Hang Guo <cshguo@gmail.com>, Zongwei Wu(zongwei.wu@uni-wuerzburg.de), and Radu Timofte <Radu.Timofte@uni-wuerzburg.de> from ETH Zurich, the University of Trento/Pisa, Tsinghua University, and the University of Wurzburg) 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.
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 super-resolve an input image to an output image with a magnification factor x4 while the proposed solution is constrained on the following aspects: inference time, number of parameters, FLOPs, fidelity (PSNR), and the challenge is called efficient super-resolution.
The focus of the contest: it will be made available DIV2K and LSDIR datasets adapted for the specific needs of the challenge. The images in the two datasets have a large diversity of contents. Both datasets are divided into training, validation, and testing data. The challenge has one track. The aim is to devise a network that reduces one or several aspects such as runtime, parameters, and FLOPs of EFDN (https://arxiv.org/pdf/2204.08759) while at least maintaining a PSNR of 26.90dB on the DIV2K_LSDIR validation dataset, and a PSNR of 26.99 on the DIV2K_LSDIR test dataset. 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, the number of parameters, 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.
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.
You are eligible to register and compete in this contest only if you meet all the following requirements:
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 the contest and get ranked, however, if you 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 the final test phase. However, 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)
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 eligible for prizes, the participants' scores 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 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.
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:
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 us 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-sponsorโs representatives in the course of entering, or what our representatives will remember about your entry. You also understand that we will not restrict the work assignments of representatives or our co-sponsorโs representatives who have had access to your entry. By entering this contest, you agree that the use of information in our representativesโ or our co-sponsorโs 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.
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.
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 competition track based on 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 the 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.
The financial sponsors of this contest are listed on NTIRE 2025 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 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 competition (tentative, the prizes depend on attracted funds from the sponsors)
Publishing papers is optional and will not be a condition to entering the challenge or winning prizes. The top-ranking participants are invited to submit a paper following CVPR2025 author rules, for peer-reviewing to the NTIRE workshop.
The results of the challenge will be published together with NTIRE 2025 workshop papers in the 2025 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 2025 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.
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 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, liability/publicity release, and applicable tax forms. If you are a potential winner and are a minor in your place of residence, we require that your parent or legal guardian 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 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, of the AIM 2019, 2020, 2021, 2022, 2023 and 2024 challenges and of the NTIRE 2017, 2018, 2019, 2020, 2021, 2022, 2023 and 2024 challenges.
The NTIRE challenge on Efficient Super-Resolution is organized jointly with the NTIRE 2025 workshop. The results of the challenge will be published at the NTIRE 2025 workshop and in the CVPR 2025 Workshops proceedings.
Yawei Li (yawei.li [at] vision.ee.ethz.ch), Bin Ren (bin.ren [at] unitn.it), Hang Guo (cshguo [at] gmail.com), Zongwei Wu (zongwei.wu [at] uni-wuerzburg.de)and Radu Timofte (Radu.Timofte [at] uni-wuerzburg.de) are the contact persons and direct managers of the NTIRE challenge.
More information about the NTIRE workshop and challenge organizers is available here: https://cvlai.net/ntire/2025/
Start: Feb. 1, 2025, 11:59 p.m.
Start: March 7, 2025, 5:59 p.m.
March 21, 2025, 11:59 p.m.
You must be logged in to participate in competitions.
Sign In