AI RESEARCH
WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models
arXiv CS.CV
•
ArXi:2603.17680v1 Announce Type: new Existing vision-language models (VLMs) have nstrated 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