University Tuebingen University of Ljubljana LOOKOUT Luxonis Shield AI Catskill AI Virginia Tech Dartmouth College Helmut-Schmidt-Universität Hamburg FBK KIT Southampton Oulu Lisboa CEVI KLE Tech BMWi

5th Workshop on Maritime Computer Vision (MaCVi)

MaCVi @ WACV 2027

Challenges / LOOKOUT visual odometry

LOOKOUT: Maritime Monocular Visual Odometry

Recover a camera trajectory from video recorded aboard a moving boat.

Water reflections, waves, changing visibility and distant shorelines make visual odometry challenging at sea. This challenge explores how well monocular methods can track motion using the visual structure available in real maritime scenes, including RGB and thermal imagery.

Development release in preparation. The public starter preview is available now: explore the code, try the synthetic evaluator example and prepare your inference environment. Real video downloads and a reproduced public-data baseline will follow. Participation dates will be announced separately.

Explore the starter and try the evaluator Follow release updates

Task and inputs

Estimate a timestamped camera-position trajectory for each monocular video clip. Allowed inference inputs are the video, camera calibration and decoded frame timestamps. GPS, IMU, AIS, speed, heading and other clip-specific navigation signals are excluded. Reference trajectories are separate evaluation labels.

Development dataset

The planned development selection contains 75 training and 20 validation clips, split by recording boat. It includes RGB and thermal recordings. The released manifest will define the final selection and camera coverage. Test data will remain withheld.

Each anonymous sequence will include video, frame timestamps, camera calibration and a local reference-position trajectory. Calibration is nominal and derived from the camera field of view. Reference positions are in metres with a local origin; the vertical coordinate is zero.

Getting started

You can start today: clone the public starter and follow its README to run a synthetic trajectory through the evaluator using only Python and NumPy. This exercises the prediction format and scoring workflow without a GPU or dataset download. It is an artificial example, not a real-data baseline.

The starter provides a DPVO baseline, independent inference and local evaluation commands, and a pinned setup guide. Inference requires the documented CUDA environment; local evaluation needs Python and NumPy. Once the release is available:

  1. Download the package, read its release terms and verify CHECKSUMS.sha256.
  2. Follow QUICKSTART.md to install the inference environment and obtain the upstream checkpoint.
  3. Run a sample clip, then score it locally against its separate reference.
  4. Develop on the training split and report results and coverage on the validation split.
python starter/infer.py --dataset release_manifest.json --clips clip_000 --output runs/demo
python starter/evaluate.py --dataset release_manifest.json --clips clip_000 --predictions runs/demo

Prediction format

Provide one JSON prediction per sequence with key, frame_indices, times and positions. Positions are finite three-dimensional points in one consistent coordinate system. Frame indices identify decoded source-video frames, and times must match their released timestamps. The package quick start specifies the full format.

Local evaluation

The evaluator aligns each predicted trajectory to the reference using one global similarity transform, including scale. It measures the difference in relative position displacement over eligible 100–800 metre reference-path segments and reports mean drift as a percentage of segment length. This is a position-only metric inspired by KITTI; orientation and absolute recovered scale are not scored. Absolute trajectory error is also reported.

Report the expected, scored and unscored clip counts together with drift. Missing predictions and failed clips are recorded explicitly; summary drift statistics cover scored clips only. Temporal coverage must accompany results. The development release does not define an official ranking, failure penalty or minimum-coverage threshold.

Training and release terms

Train on the supplied training split. External pretraining is allowed and must be disclosed. Validation references may be used for development and evaluation, but do not train on validation or test videos, including through self-supervised training. Read RULES.md and the supplied LICENSE.txt before using the release.

Updates and support

Follow the MaCVi Discord community for release updates or ask questions in the MaCVi support forum. The first release supports local development. Online submission and leaderboard support will follow.