4 papers
ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability Awareness
Qiao Yan, Yihan Wang, Zhenghao Xing +2
Autonomous driving under adverse weather remains a critical challenge, yet existing vision-language benchmarks mainly evaluate under standard conditions, synthetic corruptions, or…
Unifying Physically-Informed Weather Priors in A Single Model for Image Restoration Across Multiple Adverse Weather Conditions
Jiaqi Xu, Xiaowei Hu, Lei Zhu +1
Image restoration under multiple adverse weather conditions aims to develop a single model to recover the underlying scene with high visibility. Weather-related artifacts vary with…
MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models
Qiao Yan, Yuchen Yuan, Xiaowei Hu +6
The increasing use of vision-language models (VLMs) in healthcare applications presents great challenges related to hallucinations, in which the models may generate seemingly plaus…
Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models
Jiaqi Xu, Mengyang Wu, Xiaowei Hu +3
This paper addresses the limitations of adverse weather image restoration approaches trained on synthetic data when applied to real-world scenarios. We formulate a semi-supervised…