# NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge Report

arXiv: https://arxiv.org/abs/2604.17070 · HTML: https://mlsanity.com/paper/2604.17070/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 80 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Builds on (most cited first, 30 of 32)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [Video Instance Segmentation](https://mlsanity.com/paper/1905.04804/) (2019)
- [Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform](https://mlsanity.com/paper/2110.05802/) (2021)
- [YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception](https://mlsanity.com/paper/2506.17733/) (2025)
- [The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report](https://mlsanity.com/paper/2604.03198/) (2026)
- [NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild](https://mlsanity.com/paper/2604.11487/) (2026)
- [NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results](https://mlsanity.com/paper/2604.06945/) (2026)
- [NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)](https://mlsanity.com/paper/2604.09030/) (2026)
- [NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods](https://mlsanity.com/paper/2604.10321/) (2026)
- [NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results](https://mlsanity.com/paper/2604.10551/) (2026)
- [NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results](https://mlsanity.com/paper/2604.10634/) (2026)
- [The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results](https://mlsanity.com/paper/2604.10532/) (2026)
- [The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results](https://mlsanity.com/paper/2604.11998/) (2026)
- [NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)](https://mlsanity.com/paper/2604.11230/) (2026)
- [NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)](https://mlsanity.com/paper/2604.12512/) (2026)
- [The Fourth Challenge on Image Super-Resolution (×4) at NTIRE 2026: Benchmark Results and Method Overview](https://mlsanity.com/paper/2604.14558/) (2026)
- [NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results](https://mlsanity.com/paper/2604.14816/) (2026)
- [Automated Rip Current Detection with Region based Convolutional Neural Networks](https://mlsanity.com/paper/2102.02902/) (2021)
- [AIM 2025 Rip Current Segmentation (RipSeg) Challenge Report](https://mlsanity.com/paper/2508.13401/) (2025)
- [RipViz: Finding Rip Currents by Learning Pathline Behavior](https://mlsanity.com/paper/2302.12983/) (2023)
- [Rip Current Segmentation: A Novel Benchmark and YOLOv8 Baseline Results](https://mlsanity.com/paper/2504.02558/) (2025)

## Built on by (most cited first, 8 of 8)

- [Low Light Image Enhancement Challenge at NTIRE 2026](https://mlsanity.com/paper/2604.17669/) (2026)
- [The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview](https://mlsanity.com/paper/2604.21312/) (2026)
- [The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview](https://mlsanity.com/paper/2604.17306/) (2026)
- [Robust Deepfake Detection, NTIRE 2026 Challenge: Report](https://mlsanity.com/paper/2604.24163/) (2026)
- [The First Controllable Bokeh Rendering Challenge at NTIRE 2026](https://mlsanity.com/paper/2605.05510/) (2026)
- [The Third Challenge on Image Denoising at NTIRE 2026: Methods and Results](https://mlsanity.com/paper/2606.16031/) (2026)
- [NTIRE 2026 Challenge on Efficient Low Light Image Enhancement: Methods and Results](https://mlsanity.com/paper/2605.02212/) (2026)
- [NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge](https://mlsanity.com/paper/2608.09782/) (2026)

## Abstract (arXiv)

This report presents the NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge, which targets automatic rip current understanding in images. Rip currents are hazardous nearshore flows that cause many beach-related fatalities worldwide, yet remain difficult to identify because their visual appearance varies substantially across beaches, viewpoints, and sea states. To advance research on this safety-critical problem, the challenge builds on the RipVIS benchmark, evaluating both detection and segmentation. The dataset is diverse, sourced from more than 10 countries, with 4 camera orientations and diverse beach and sea conditions. This report describes the dataset, challenge protocol, evaluation methodology, final results, and summarizes the main insights from the submitted methods. The challenge attracted 159 registered participants and produced 9 valid test submissions across the two tasks. Final rankings are based on a composite score that combines F1[50], F2[50], F1[40!:!95], and F2[40!:!95]. Most participant solutions relied on pretrained models, combined with strong augmentation and post-processing design. These results suggest that rip current understanding benefits strongly from the robust general-purpose vision models' progress, while leaving ample room for future methods tailored to their unique visual structure.