The 4th Workshop on Maritime Computer Vision (MaCVi) is organized as part of CVPR 2026. This edition features five benchmark challenges with emphasis on both predictive accuracy and embedded real-time feasibility. This report summarizes the MaCVi 2026 challenge setup, evaluation protocols, datasets, and benchmark tracks, and presents quantitative results, qualitative comparisons, and cross-challenge analyses of emerging method trends. We also include technical reports from top-performing teams to highlight practical design choices and lessons learned across the benchmark suite. Datasets, leaderboards, and challenge resources are available at https://macvi.org/workshop/cvpr26.
@article{arxiv.2604.13244,
title = {4th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview},
author = {Benjamin Kiefer and Jan Lukas Augustin and Jon Muhovič and Mingi Jeong and Arnold Wiliem and Janez Pers and Matej Kristan and Alberto Quattrini Li and Matija Teršek and Josip Šarić and Arpita Vats and Dominik Hildebrand and Rafia Rahim and Mahmut Karaaslan and Arpit Vaishya and Steve Xie and Ersin Kaya and Akib Mashrur and Tze-Hsiang Tang and Chun-Ming Tsai and Jun-Wei Hsieh and Ming-Ching Chang and Wonwoo Jo and Doyeon Lee and Yusi Cao and Lingling Li and Vinayak Nageli and Arshad Jamal and Gorthi Rama Krishna Sai Subrahmanyam and Jemo Maeng and Seongju Lee and Kyoobin Lee and Xu Liu and LiCheng Jiao and Jannik Sheikh and Martin Weinmann and Ivan Martinović and Jose Mateus Raitz Persch and Rahul Harsha Cheppally and Mehmet E. Belviranli and Dimitris Gahtidis and Hyewon Chun and Sangmun Lee and Philipp Gorczak and Hansol Kim and Jeeyeon Jeon and Borja Carrillo Perez and Jiahui Wang and Sangmin Park and Andreas Michel and Jannick Kuester and Bettina Felten and Wolfgang Gross and Yuan Feng and Justin Davis},
journal= {arXiv preprint arXiv:2604.13244},
year = {2026}
}
Comments
Accepted to CVPR 2026 Workshop Proceeding; Maritime Computer Vision Workshop