AIM 2020 Rendering Realistic Bokeh Challenge - Track 2: on smartphone GPU

Organized by Radu - Current server time: Jan. 19, 2021, 8:28 p.m. UTC


July 10, 2020, 11:59 p.m. UTC


May 9, 2020, 11:59 p.m. UTC


Competition Ends
July 20, 2020, 11:59 p.m. UTC

AIM Workshop and Challenge @ ECCV 2020


Rendering Realistic Bokeh Challenge


Important dates


  • 2020.05.08 Release of train data (input and output images) and validation data (only input)
  • 2020.05.15 Validation server online
  • 2020.07.10 Final test data release (inputs only)
  • 2020.07.20 Test output results submission deadline (EXTENDED)
  • 2020.07.20 Fact sheets and code/executable submission deadline (EXTENDED)
  • 2020.07.22 Preliminary test results release to the participants (EXTENDED)
  • 2020.07.29 Paper submission deadline for entries from the challenge
  • 2020.08.28 AIM workshop and challenges, results and award ceremony (ECCV 2020, Glasgow, UK)


Challenge overview

The 2nd edition of AIM: Advances in Image Manipulation workshop  will be held August 28, 2020 in conjunction with ECCV 2020 in Glasgow, UK.

Bokeh is an important artistic effect used to highlight the main object of interest on the photo by blurring out-of-focus areas. While DSLR cameras can produce this effect naturally, it is still unattainable for mobile devices due to their compact optics and tiny camera sensors. The recently presented computational bokeh effect rendering methods are also not able to generate realistic shallow depth-of-field images since they are producing a simple flat background blur that is very different from the real bokeh on DSLR photos. To address this problem, we present a large-scale Everything is Better with Bokeh! (EBB!) dataset consisting of 5 thousand aligned wide / shallow depth-of-field image pairs captured using the Canon 7D DSLR with 50mm f/1.8 lenses, and propose the participants to use this data to train their own deep learning-based bokeh effect rendering models.

The challenge has two tracks:

  • Track 1, "CPU Inference": the target is to achieve a Bokeh effect image with the best perceptual quality similar to the ground truth as measured by the Mean Opinion Score (MOS). In addition, efficient solutions are sought, the inference time of each solution will be measured on standard desktop CPUs.
  • Track 2, "Smartphone GPU Inference": while the target here is the same as in the first track, in this case the speed of all proposed solutions will be measured on smartphone GPUs. For this, the participants also need to submit the corresponding TensorFlow Lite models that will be later executed directly on several Android devices using the TFLite GPU delegate. TensorFlow / Keras users can convert their models to .tflite format using just two lines of code, while PyTorch developers have to export their models to ONNX and then convert the resulting model to TFLite.

The top ranked participants in each track will be awarded and invited to submit a paper describing their solution to the associated AIM workshop at ECCV 2020. The workshop is aimed at providing an overview of the new trends and advances in the image reconstruction domain and offers an opportunity for academic and industrial attendees to interact and explore collaborations.

Note that for the final ranking and challenge winners, we are weighing more the teams / participants with entries in more than one track challenge. Ideally, each participant will have entries for both tracks.

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



To learn more about each competition, to participate in the challenge, and to access the newly collected EBB! dataset with Bokeh and Bokeh-free images everybody is invited to register at the following links, accordingly:

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

Related literature

Rendering Natural Camera Bokeh Effect With Deep Learning, CVPR Workshops 2020

Aim 2019 challenge on bokeh effect synthesis: Methods and results, ICCV Workshops 2019

Provided Resources

  • Scripts: With the dataset the organizers will provide scripts to facilitate the reproducibility of the images and performance evaluation results after the validation server is online. 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 (Andrey [at] and Radu.Timofte [at] if you have doubts or any question.

AIM Workshop and Challenge @ ECCV 2020


Rendering Realistic Bokeh Challenge



The evaluation consists from the comparison of the synthesized Bokeh images with the ground truth Bokeh images.

For the Track 1 we use the Mean Opinion Score (MOS) for perceptual quality and the runtime on CPU.

For the Track 2 we use the Mean Opinion Score (MOS) for perceptual quality and the runtime on smartphone GPU.

However, since MOS requires opinions from human subjects, a user study will be conducted only on the final test images, for the final ranking. Meanwhile, we will report the standard Peak Signal To Noise Ratio (PSNR) and the Structural Similarity (SSIM) index as often employed in the literature. Implementations are found in most of the image processing toolboxes. For each dataset we report the average results over all the processed images belonging to it.

For submitting the results, you need to follow these steps:

  1. process the input Bokeh-free images and keep the same name for the Bokeh image results as produced by your method (example: for an input file with name "083.png" the output file should be "083.png") 
    Note that the output Bokeh images should be saved with lossless compression and should have the size of the input Bokeh-free images.
  2. create a ZIP archive containing all the Bokeh image results named as above and a readme.txt Note that the archive should not include folders, all the images/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.

Advances in Image Manipulation (AIM) challenge on rendering realistic bokeh @ ECCV 2020


Example-based Rendering Realistic Bokeh Challenge

These are the official rules (terms and conditions) that guvern how the AIM challenge on example-based bokeh effect 2020 will operate. This challenge will be simply reffered to as the "challenge" or the "contest" throghout the remaining part of these rules and may be named as "AIM" or "EBB!" benchmark, challenge, or contest, elsewhere (our webpage, our documentation, other publications).

In these rules, "we", "our", and "us" refer to the organizers (Radu Timofte and Andrey Ignatov from ETH Zurich, CVL) of AIM 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 responsability of the participant to send an email to the organizers (Andrey [at] and Radu.Timofte [at] 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 the manipulation of a clean Bokeh-free image by addition of a synthesized Bokeh effect and the challenge is called rendering realistic Bokeh.

Focus of the contest: it will be made available a newly collected dataset of at least 5000 newly collected image pairs adapted for the specific needs of the challenge. The images are 1024 pixels on vertical direction and have a large diversity of contents. We will refer to this dataset, its partition, and related materials as Everything is Better with Bokeh! or EBB! (5K+ Bokeh and Bokeh-free image pairs dataset). The dataset is divided into training, validation and testing data. We focus on two distinct settings:  (track 1: on CPU) example-based Bokeh effect where the targets are the perceptual quality of the output Bokeh image results in comparison to the ground truth Bokeh images and the inference time achieved on CPU, and (track 2: on smartphone GPU) same as for track 1 only running on smartphone GPUs. The participants will not have access to the ground truth Bokeh images from the test data. For each track 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 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 AIM 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 AIM challenge organizer or an employee of AIM 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 AIM 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 AIM 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 AIM 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 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 ( 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 AIM Workshop and Challenges (to be held on August 28, 2020, Glasgow, UK). 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 AIM 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. AIM 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 AIM 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 validation dataset will be released at the start of the final phase when the test data without ground truth images will be made available.
      • Post-challenge analyses: 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 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 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-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 AIM 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 AIM 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 to entering the challenge or winning prizes. The top ranking participants are invited to submit a paper following ECCV2020 author rules for peer-reviewing to AIM workshop.

The results of the challenge will be published together with AIM 2020 workshop paper in the 2020 ECCV 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 ECCV 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, 2019 and 2020 challenges .

AIM Workshop and Challenge @ ECCV 2020




The AIM challenge on rendering realistic Bokeh is organized jointly with the AIM 2020 workshop. The results of the challenge will be published at AIM 2020 workshop and in the ECCV 2020 Workshops proceedings.


Andrey Ignatov (andrey [at] and Radu Timofte (Radu.Timofte [at] are the contact persons and direct managers of the AIM challenge.


More information about AIM workshop and challenge organizers is available here:


Start: May 9, 2020, 11:59 p.m.


Start: July 10, 2020, 11:59 p.m.

Competition Ends

July 20, 2020, 11:59 p.m.

You must be logged in to participate in competitions.

Sign In