Adverse-to-the-eXtreme Panoptic Segmentation: URVIS 2026 Study and Benchmark

TL;DR

This paper reports on the URVIS 2026 challenge focused on robust panoptic segmentation across adverse weather conditions using multimodal sensor data, establishing a new benchmark and evaluating current methods.

Contribution

It introduces the first challenge of its kind on adverse weather panoptic segmentation, utilizing the MUSES dataset and proposing the weighted Panoptic Quality metric for evaluation.

Findings

17 participants and 47 submissions in the challenge

Performance analysis of submitted methods across weather conditions

Discussion of progress and remaining challenges in multimodal segmentation

Abstract

This paper presents the report of the URVIS 2026 challenge on adverse-to-extreme panoptic segmentation. As the first challenge of its kind, it attracted 17 registered participants and 47 submissions, with 4 teams reaching the final phase. The challenge is based on the MUSES dataset, a multi-sensor benchmark for panoptic segmentation in adverse-to-extreme weather, including RGB frame camera, LiDAR, radar, and event camera data. Weighted Panoptic Quality (wPQ) is designed and adopted as the official ranking metric for fair evaluation across weather conditions. In this report, we summarise the challenge setting and benchmark results, analyse the performance of the submitted methods, and discuss current progress and remaining challenges for robust multimodal panoptic segmentation. Link: https://urvis-workshop.github.io/challenge-Muses.html