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

TL;DR

The NTIRE 2026 Rip Current Detection and Segmentation Challenge advances automatic rip current understanding using a diverse dataset, with solutions mainly leveraging pretrained models and data augmentation, highlighting progress and future potential.

Contribution

This challenge introduces a new diverse dataset and evaluation protocol for rip current detection and segmentation, fostering research with pretrained models and highlighting future directions.

Findings

Most solutions used pretrained models with augmentation.

Participants achieved improved detection and segmentation performance.

Results indicate robust general-purpose models benefit rip current understanding.

Abstract

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 $F_1[50]$, $F_2[50]$, $F_1[40\!:\!95]$, and $F_2[40\!:\!95]$. 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.