Challenge

Together with the workshop, we will run the 3rd re-localization challenge for autonomous driving based on the 4Seasons dataset. The goal of the challenge is to estimate the 6DOF relative pose between individual images from a reference sequence to a target sequence. The winner of the challenge will receive 1000 USD, and the second place will receive 500 USD.

Evaluation

For the challenge, we will evaluate the re-localization accuracy of a method given a pair of reference and query images (defined in the re-localization file). For each pair of the re-localization file, we evaluate the translational error between the estimated and the ground truth pose, respectively.

Dataset

The sequences for the challenge are based on the 4Seasons dataset.

While the 4Seasons dataset consists of numerous sequences for which reference poses are provided and therefore can be used for training, we will use three different scenarios, each consisting of a reference map and a query sequence for the challenge.

For the specific reference and query pairs, we refer to this GitHub repository.

Submission

Please submit your results as a single .zip file. The results for each re-localization file must be stored in a separate .txt file in the archive's root folder. The file name must be exactly like the provided ones (case-sensitive).

The file format should be a text-file containing one re-localization pair per line. Each line must contain 9 values:

source_kf target_kf t_x t_y t_z q_x q_y q_z q_w

In order to submit your results, you will have to send an email with the single .zip file which contains the re-localization results for the 3 provided files.

Send to: mlad-eccv2022@googlegroups.com.

Rules

If you want to participate in the challenge, you need to describe your approach in a publication. This can be in the form of a published conference or journal paper (incl. ECCV2022), a pre-print paper on arXiv, or a regular submission to our workshop.
You are not allowed to hand in results obtained with open-source projects without any added novelty.
Both, the winner, and the second place of the challenge must attend the workshop and present their approach (one member is sufficient)
The use of additional training data or the use of pre-trained models is allowed. However, one needs to specify which data was used to train the models. Using the test sequence for training is not allowed.

Deadlines

Challenge deadline: October 14, 2022

For questions, please email mlad-eccv2022@googlegroups.com.

Results

Localization thresholds: 0.1 m, 0.25 m, 1 m