Dear participants,
We are excited to share the final results of the 2025 Night Photography Rendering Challenge.
A total of 10 submissions were received by the deadline. All of the submissions outperformed the baseline solution in both objective metrics and perceptual quality and thus will be included in the report.
The winners of objective metric evaluation category are:
The detailed results are presented below.
Team | SSIM | SSIMRank | PSNR | PSNRRank | Final Score |
---|---|---|---|---|---|
NJUST_KMG | 0.810 | 1 | 23.82 | 1 | 1.0 |
Mialgo | 0.799 | 2 | 23.06 | 2 | 2.0 |
PSU Team | 0.774 | 3 | 22.21 | 3 | 3.0 |
psykhexx | 0.771 | 4 | 21.69 | 4 | 4.0 |
POLYU-AISP | 0.758 | 6 | 21.23 | 5 | 5.6 |
sorange | 0.760 | 5 | 20.91 | 7 | 5.8 |
NoTeam | 0.722 | 7 | 21.22 | 6 | 6.6 |
AITH_ITMO | 0.718 | 8 | 20.58 | 8 | 8.0 |
colab | 0.656 | 9 | 19.15 | 9 | 9.0 |
OzU-VGL | 0.640 | 10 | 17.18 | 10 | 10.0 |
Baseline | 0.386 | 9.55 |
The winners of perceptual quality evaluation category are:
The detailed results are presented below.
Team | Score |
---|---|
Mialgo | 128.49 |
NJUST_KMG | 123.73 |
PSU Team | 116.60 |
psykhexx | 106.43 |
POLYU-AISP | 101.44 |
sorange | 95.65 |
AITH_ITMO | 73.68 |
colab | 64.14 |
NoTeam | 58.58 |
OzU-VGL | 35.56 |
Baseline | 6.53 |
The winners will be informed on how to receive their prizes in the upcoming days.
We sincerely congratulate the winners and thank all teams for participating in our challenge. We wish you the best of luck in all your future endeavors.
Best regards,
The NTIRE Night Photography Rendering Challenge Team
Dear participants,
we announce the start of the final Testing phase of our challenge. To participate in the final checkpoint two conditions must be met:
Note the following:
We also impose an additional rule for evaluation regarding tie breaks. If two teams tie for a podium place (1st - 3rd), the winner of the tie will be the team with higher SSIM. Otherwise, teams will share a tied place.
The results will be available on the CodaLab page and on the official webpage of the challenge after evaluation.
If you have any additional questions, please let us know. We wish you the best of luck!
Dear participants,
We are excited to share the intermediate results of our competition based on the Validation 4 checkpoint.
For this evaluation, we considered all relevant solutions submitted before 14.03.2025, 00:00 UTC+0. A total of 11 submissions were received by the deadline.
We remind you that for objective metric evaluation, your final score is given by 0.4 * PSNRRank + 0.6 * SSIMRank. The standings are as follows:
Participant | PSNR | PSNR Rank | SSIM | SSIM Rank | Final Score |
---|---|---|---|---|---|
Daniil_S | 21.60 | 1 | 0.731 | 1 | 1.0 |
Gideon | 21.35 | 2 | 0.730 | 2 | 2.0 |
Stangeriness | 20.44 | 3 | 0.728 | 3 | 3.0 |
ps | 20.41 | 4 | 0.703 | 4 | 4.0 |
AnasM | 20.12 | 5 | 0.702 | 5 | 5.0 |
MaXiaoyang | 19.77 | 7 | 0.697 | 6 | 6.4 |
zongqihe | 19.89 | 6 | 0.695 | 8 | 7.2 |
gwxysyhljt | 19.44 | 8 | 0.696 | 7 | 7.4 |
camera_mi | 17.95 | 9 | 0.668 | 9 | 9.0 |
gwan | 17.28 | 10 | 0.630 | 10 | 10.0 |
azwaad.mohiuddin | 7.71 | 11 | 0.120 | 11 | 11.0 |
We remind you that for the perceptual quality evaluation, we conduct a pairwise comparison of images generated by the solutions against the original DSLR images. Survey participants were asked to select which image in each pair better matched the original DSLR image. The score represents the average win percentage across all evaluated images. The standings are as follows:
Participant | Score |
---|---|
Gideon | 116.51 |
Daniil_S | 106.90 |
Stangeriness | 99.25 |
zongqihe | 88.62 |
ps | 80.50 |
gwxysyhljt | 75.57 |
MaXiaoyang | 71.37 |
gwan | 54.34 |
AnasM | 47.18 |
camera_mi | 43.50 |
azwaad.mohiuddin | 0.56 |
Soon we will allow submissions for the final testing. Please be ready to submit your solutions as docker containers as well as reports describing your solution.
Thank you for participating and best of luck in the final checkpoint!
Dear participants,
we are happy to anounce the start of the Validation 4 checkpoint. You can find the data at the Participate/Get Data section of the CodaLab page. Please submit your solutions until 13.03.2025 23:59 UTC+0.
Due to certain issues with CodaLab website and in preparation to the final Testing phase we provide an alternative way to submit your solution. You can fill out the form below and attach the resulting images as well as your docker solutions. Docker containers are not required for this checkpoint, however we encourage you to provide them as it will streamline the process of running your final solutions. Instructions can be found in the form.
Responses submitted through the form will be run manually. Due to that, participants are limited to two solutions per day. Please only employ this method of submission when submitting through CodaLab is impossible. The results will be maintained in a table on the CodaLab page. Please note that it will not be updated in real-time.
Solutions sent through both CodaLab and Google Forms will be eligible for participating in Validation 4 checkpoint MOS evaluation. The last solution (between CodaLab and Forms) will be used for evaluation.
We remind you that submitting your docker solutions as well as reports will be necessary for participating in the Testing phase.
We wish you the best of luck.
Google Forms Leaderboard (last upadated on 13.03.2025 17:30 UTC+0)
Participant | PSNR | SSIM |
---|---|---|
NJUST-KMG | 20.33 | 0.72 |
CajunDADL | 9.41 | 0.13 |
Dear participants,
We are excited to share the intermediate results of our competition based on the Validation 3 checkpoint.
For this evaluation, we considered all relevant solutions submitted before 05.03.2025, 00:00 UTC+0. A total of 8 submissions were received by the deadline. Participants who were unable to submit on time are encouraged to take part in the upcoming Validation 4 checkpoint.
We remind you that for objective metric evaluation, your final score is given by 0.4 * PSNRRank + 0.6 * SSIMRank. The standings are as follows:
Participant | PSNR | PSNR Ranking | SSIM | SSIM Ranking | Final Score |
---|---|---|---|---|---|
Hazzy | 21.34 | 2 | 0.73 | 1 | 1.4 |
Daniil_S | 22.12 | 1 | 0.72 | 3 | 2.2 |
Stangeriness | 21.24 | 3 | 0.73 | 2 | 2.4 |
Gideon | 21.20 | 4 | 0.72 | 4 | 4.0 |
AnasM | 18.79 | 6 | 0.68 | 5 | 5.4 |
mialgo_ls | 18.84 | 5 | 0.64 | 7 | 6.2 |
camera_mi | 18.47 | 8 | 0.66 | 6 | 6.8 |
gwxysyhljt | 18.69 | 7 | 0.64 | 8 | 7.6 |
For the perceptual quality evaluation, we conducted a pairwise comparison of images generated by the solutions against the original DSLR images. Participants were asked to select which image in each pair better matched the original DSLR image. The score represents the average win percentage across all evaluated images. The standings are as follows:
Participant | Score |
---|---|
Gideon | 52.29 |
Hazzy | 45.66 |
Daniil_S | 42.23 |
Stangeriness | 40.42 |
gwxysyhljt | 23.51 |
mialgo_ls | 23.15 |
camera_mi | 17.39 |
AnasM | 16.26 |
We remind you that the data for the next Validation 4 checkpoint will be released soon. Thank you for participating in our challenge!
Dear participants,
we notify you that due to certain techical difficulties we have experienced with collecting MOS scores the results are delayed. We deeply apologize for this inconvenience. The results will be made available as soon as possible.
To accomodate this issue, the release and the deadline for the fourth validation checkpoint will be adjusted. The checkpoint data will be released on 11.03.2025 and the solutions will be due 13.03.2025. Please see the updated timeline.
To stimulate development of your solutions, we decided to release additional data. Camera images for the Validation 2 checkpoint are made available to you. Together with raw images from the Validation 2 checkpoint, they can be used as additional training data for your models. The download link in the "Get Data" section of the CodaLab page.
We will soon provide details on how to submit your final docker solutions and reports. Thank you for your interest in our challenge.
Dear participants,
we want to notify you about important changes coming to our challenge. Due to not being able to collect MOS during the Validation 2 checkpoint, we decided to add an additional Validation 4 checkpoint that will also include MOS calculation. That is so you can receive additional feedback on your solutions.
This also implies changes to the timeline. The testing phase will be postponed. Please see the updated timeline.
Finally we anounce how your final ranking in the objective metric leaderboard be evaluated. First, all participants wil be ranked based on their PSNR and SSIM scores; each participant will receive a PSNRRank and SSIMRank. Final score is calculated as Score = 0.4 * PSNRRank + 0.6 * SSIMRank, and participants with the lowest scores will be considered winners.
If you have any questions, please let us know.
Welcome to the "Night Photography" challenge part of the NTIRE workshop at CVPR 2025. The challenge seeks to advance image processing methods for night photography by addressing the complexities of rendering images captured at night, particularly this year with raw mobile phone captures, and evaluating the results based on perceptual quality and computational efficiency.
The process of capturing and processing images taken by cameras relies on onboard processing to transform raw sensor data into polished photographs, typically encoded in a standard color space such as sRGB. Night photography, however, presents unique challenges not encountered in daylight scenes. Night images often feature complex lighting conditions, including multiple visible illuminants, and are characterized by distinctive noise patterns that make conventional photo-finishing techniques for daytime photography unsuitable. Additionally, widely used image quality metrics like SSIM and LPIPS are often ineffective for evaluating the nuances of night photography. In previous editions of this challenge, participants were tasked with processing raw night scene images into visually pleasing renders, assessed subjectively using mean opinion scores. These efforts have driven significant advancements in the field of night image processing.
This year's challenge introduces a new and fundamentally different approach while retaining the use of the mean opinion score as an evaluation metric. Moving away from purely subjective aesthetics, the 2025 challenge will adopt a potentially more objective framework by leveraging paired datasets captured with a Huawei smartphone and a high-end Sony camera using a beam splitter to ensure identical perspectives. Participants will be provided with raw Huawei smartphone images as input and corresponding processed Sony camera images as the expected output. The goal is to develop algorithms that transform the raw Huawei images—characterized by higher noise levels, vignetting, and reduced detail—into outputs that convincingly resemble the high-quality processed Sony images.
Mean opinion score will be employed to evaluate submissions, ensuring that human viewers, rather than automated metrics that might be exploited, determine how convincingly the processed Huawei images align with the processed Sony images. This focus on human perception underscores the importance of developing rendering algorithms that produce results that are not only technically accurate but also perceptually closer from the target images.
By addressing the unique limitations of mobile phone raw images and the inherent complexities of night photography, the 2025 challenge seeks to advance the state of the art in image processing. The combination of objective input-output alignment and perceptual validation through mean opinion scores provides a robust framework for fostering innovation in mobile-focused night photography rendering where objectivity has a more pronounced role, but is not expected to be abused in anyway due to the final subjective oversight.
This challenge tackles the complexities of nighttime photography by leveraging paired datasets of raw Huawei smartphone images and processed Sony camera images, providing a clear ground truth for evaluation. The goal is to develop algorithms that process raw Huawei images to convincingly resemble the high-quality Sony outputs, addressing a long-standing challenge in computer vision.
Night photography is vital for applications like surveillance and security and also has artistic significance in creating stunning images. By combining objective ground-truth comparisons with human perception through mean opinion scores, the challenge ensures that results are both technically accurate and visually convincing.
This unique framework bridges mobile device constraints, low-light conditions, and human-centric evaluation, advancing the state of the art in night image processing.
In order to be eligible for the prizes, the participants will be required to send code and reports about their solutions in the form of short papers during the submission. If this report is not submitted, the participants that would otherwise win a prize will be passed over.
There will be two prize categories:
First three places from each category will be awarded 1000 USD, 650 USD, and 350 USD for the first, second, and third place, respectively.
Winners will receive a winner certificate and will have an opportunity to submit their paper to NTIRE'2025 and participate in the common report which also will be submitted to CVPR workshop.
Please direct any and all questions at nightphotochallenge [at] gmail.com.
In this challenge, each submission will be evaluated based on:
1. Objective metrics: the standard Peak Signal To Noise Ratio (PSNR) and the Structural Similarity Index (SSIM);
2. Perceptual quality, measured by the Mean Opinion Score (MOS).
PSNR and SSIM are used as often employed in the literature. Implementations can be found in most of the image processing toolboxes. For each dataset we report the average results over all the processed images belonging to it. The evaluation of the reconstructed results consists from the comparison of the rendered smartphone images with the ground truth camera images.
These are the official rules (terms and conditions) that govern how the NTIRE Workshop 2025 challenge on Night Photography Rendering 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 "Night Photography Rendering" benchmark, challenge, or contest, elsewhere (our webpage, our documentation, other publications).
In these rules, "we", "our", and "us" refer to the organizers (nightphotochallenge [at] gmail.com) 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 render an sRGB image from provided RAW input and the challenge is called Night Photography Rendering.
Focus of the contest: it will be made available a 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 the Night Photography Rendering Dataset. The dataset is divided into training, validation, and testing data. We focus on the perceptual quality of the results, the aim is to achieve RGB images with the best fidelity (PSNR+SSIM or MOS) to the reference ground truth from the DSLR camera. 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 winners will be determined according to their entries, the reproducibility of the results and uploaded codes, 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 Night Photography Rendering 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 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.
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. Please note that code of the top-ranking participants (three top participants in each category) will be publicly released and made online accessible. 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 online in 2025).
Use of data provided: all data provided by NTIRE are freely available to the participants from the website of the challenge. 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.
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 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.
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 financial sponsors of this contest are listed on Night Photography Rendering Challenge web page.
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 paper following CVPR 2025 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 on the competition page and/or 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 will be delivered to the registered team leader given that the team is not affiliated with any of the sponsors. It is 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 challenges .
The Night Photography Rendering challenge is organized jointly with the NTIRE 2025 workshop. The results of the challenge will be published at the CVPR 2025 workshops proceedings.
Please direct any and all questions at nightphotochallenge [at] gmail.com.
More information about NTIRE workshop and challenge organizers is available here: https://cvlai.net/ntire/2025/.
This challenge is powered by Artificial Intelligence Research Institute (AIRI Institute).
List of organizers:
Start: Feb. 7, 2025, 11:59 p.m.
Start: Feb. 18, 2025, 11:59 p.m.
Start: March 2, 2025, 11:59 p.m.
Start: March 11, 2025, 11:59 p.m.
March 24, 2025, 11:59 p.m.
You must be logged in to participate in competitions.
Sign In