3rd Workshop on Maritime Computer Vision (MaCVi) 2025: Challenge Results
Not on the map. Why?
Abstract (arXiv)
The 3rd Workshop on Maritime Computer Vision (MaCVi) 2025 addresses maritime computer vision for Unmanned Surface Vehicles (USV) and underwater. This report offers a comprehensive overview of the findings from the challenges. We provide both statistical and qualitative analyses, evaluating trends from over 700 submissions. All datasets, evaluation code, and the leaderboard are available to the public at https://macvi.org/workshop/macvi25.
Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 50 of its 85 references that are in the map. First posted on arXiv 17 Jan 2025.
Builds on
50 of 85 references.
References · 50
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 2020End-to-End Object Detection with Transformerscited by 7,414
- 2016Feature Pyramid Networks for Object Detectioncited by 5,036
- 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
- 2022A ConvNet for the 2020scited by 3,579
- 2016Gaussian Error Linear Units (GELUs)cited by 3,502
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
38 more
- 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
- 2017Decoupled Weight Decay Regularizationcited by 1,831
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
- 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
- 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
- 2022Reproducible scaling laws for contrastive language-image learningcited by 1,173
- 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
- 2018Panoptic Segmentationcited by 802
- 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 723
- 2022Simple Baselines for Image Restorationcited by 708
- 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 596
- 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
- 2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 473
- 2023Symbolic Discovery of Optimization Algorithmscited by 434
- 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 429
- 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 344
- 2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPcited by 201
- 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
- 2015A Novel Performance Evaluation Methodology for Single-Target Trackerscited by 113
- 2021From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Datacited by 68
- 2021SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Watercited by 61
- 2024Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applicationscited by 50
- 2023WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfacescited by 35
- 2024NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Resultscited by 26
- 2024You Only Need One Color Space: An Efficient Network for Low-light Image Enhancementcited by 24
- 2021Leveraging Synthetic Data in Object Detection on Unmanned Aerial Vehiclescited by 22
- 2023LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and Benchmarkcited by 19
- 2024Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworkscited by 16
- 2023SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazingcited by 15
- 2018Are object detection assessment criteria ready for maritime computer vision?cited by 9
- 2021Learning Maritime Obstacle Detection from Weak Annotations by Scaffoldingcited by 8
- 2024SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimationcited by 8
- 2023The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024cited by 7
- 2023eWaSR -- an embedded-compute-ready maritime obstacle detection networkcited by 5
- 2024CasDyF-Net: Image Dehazing via Cascaded Dynamic Filterscited by 3
- 2024PanSR: An Object-Centric Mask Transformer for Panoptic Segmentationcited by 3
- 2025Approximate Supervised Object Distance Estimation on Unmanned Surface Vehiclescited by 3
- 2024ITP: Instance-Aware Test Pruning for Out-of-Distribution Detectioncited by 1
Built on by
Citing papers per year: 2025: 3; 2026: 1.
4 papers.
- 2025USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterwayscited by 4
- 2025Real-Time Fusion of Visual and Chart Data for Enhanced Maritime Visioncited by 2
- 2025Sea-ing Through Scattered Rays: Revisiting the Image Formation Model for Realistic Underwater Image Generationcited by 2
- 20264th Workshop on Maritime Computer Vision (MaCVi): Challenge Overviewcited by 0
- 20264th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview14 Apr 2026
- 2025Sea-ing Through Scattered Rays: Revisiting the Image Formation Model for Realistic Underwater Image Generation18 Sep 2025
- 2025Real-Time Fusion of Visual and Chart Data for Enhanced Maritime Vision18 Jul 2025
- 2025USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways23 Jun 2025