WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models

TL;DR

WeatherReasonSeg introduces a comprehensive benchmark to evaluate vision-language models' reasoning-based segmentation performance under adverse weather conditions, highlighting their robustness challenges and vulnerability patterns.

Contribution

The paper presents WeatherReasonSeg, a novel benchmark with synthetic and real-world datasets for assessing weather-aware reasoning segmentation in VLMs, including multiple reasoning dimensions.

Findings

VLM performance decreases as weather severity increases

Different weather types cause distinct vulnerability patterns

Benchmark enables detailed robustness analysis

Abstract

Existing vision-language models (VLMs) have demonstrated impressive performance in reasoning-based segmentation. However, current benchmarks are primarily constructed from high-quality images captured under idealized conditions. This raises a critical question: when visual cues are severely degraded by adverse weather conditions such as rain, snow, or fog, can VLMs sustain reliable reasoning segmentation capabilities? In response to this challenge, we introduce WeatherReasonSeg, a benchmark designed to evaluate VLM performance in reasoning-based segmentation under adverse weather conditions. It consists of two complementary components. First, we construct a controllable reasoning dataset by applying synthetic weather with varying severity levels to existing segmentation datasets, enabling fine-grained robustness analysis. Second, to capture real-world complexity, we curate a real-world adverse-weather reasoning segmentation dataset with semantically consistent queries generated via mask-guided LLM prompting. We further broaden the evaluation scope across five reasoning dimensions, including functionality, application scenarios, structural attributes, interactions, and requirement matching. Extensive experiments across diverse VLMs reveal two key findings: (1) VLM performance degrades monotonically with increasing weather severity, and (2) different weather types induce distinct vulnerability patterns. We hope WeatherReasonSeg will serve as a foundation for advancing robust, weather-aware reasoning.