5th Workshop on Maritime Computer Vision (MaCVi)
MaCVi @ WACV 2027
Challenges / LOOKOUT visual odometry
LOOKOUT: Maritime Monocular Visual Odometry
Challenge deadlines and author metadata
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.
Download development dataset (6.8 GB) SHA-256 checksum
Get the starter and setup guide Follow release updates
Challenge Schedule
| Event | Date |
|---|---|
| Author details and active OpenReview profiles confirmed | October 23, 2026, 23:59 AoE |
| All challenges close (final submission deadline) | October 27, 2026, 23:59 AoE |
| Final results and winner notification | October 30, 2026 |
You can begin developing and submitting challenge results before completing author metadata. If you need a new OpenReview account, please start registration by October 9: activation can take up to two weeks.
AoE means Anywhere on Earth (UTC−12). The organizers will hand off the summary paper's final metadata by November 2, 2026. The archival camera-ready deadline is November 20, 2026, 23:59 Pacific Time (PST, UTC−8). See the paper publication schedule for details.
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 development selection contains 68 training and 24 validation clips, split by recording boat. It includes RGB and thermal recordings. The package manifest lists every sequence and its camera mode. Test data remains withheld.
Each anonymous sequence includes 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. DPVO inference requires the documented CUDA environment; local evaluation needs Python and NumPy. To work with the real videos:
- Download the archive and its checksum, verify and extract it using the commands below, then read
LICENSE.txtandRULES.md. - Follow the public starter’s
QUICKSTART.mdto install the inference environment and obtain the upstream checkpoint. - Run a sample clip, then score it locally against its separate reference.
- Develop on the training split and report results and coverage on the validation split.
curl -fLO https://macvi.org/downloads/lookout/v0.1/lookout-vo-dev-v0.1.tar
curl -fLO https://macvi.org/downloads/lookout/v0.1/lookout-vo-dev-v0.1.tar.sha256
sha256sum --check lookout-vo-dev-v0.1.tar.sha256
tar -xf lookout-vo-dev-v0.1.tar
(cd release && sha256sum --check CHECKSUMS.sha256)
git clone https://github.com/LOOKOUT-AI/lookout-vo-challenge.git
# After following the starter's QUICKSTART.md:
python lookout-vo-challenge/starter/infer.py --dataset release/release_manifest.json --clips clip_000 --output runs/demo
python lookout-vo-challenge/starter/evaluate.py --dataset release/release_manifest.json --clips clip_000 --predictions runs/demoUse the current public starter with the downloaded manifest. See its release notes and known limitations for baseline validation updates. A fresh GPU reproduction is still pending; no official baseline score or competition ranking is claimed here.
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.
The dataset is released under
CC BY-NC 4.0;
the public starter code uses the MIT License. Upstream DPVO and checkpoint terms apply separately.
Read RULES.md and the supplied LICENSE.txt before using the release.
Updates and support
Join the MaCVi Discord community for release updates and challenge support. Please ask LOOKOUT questions in the visual-odometry-support-forum channel. The first release supports local development. Online submission and leaderboard support will follow.