SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization

Snowfall poses a significant challenge to visual data processing, requiring specialized desnowing algorithms. However, current models often struggle with generalization due to their reliance on synthetic datasets, creating a domain gap. Evaluating real snowfall images is difficult due to the lack of ground truth. To tackle these issues, we introduce a large-scale, high-quality dataset of 10,000 annotated real snow scenes, develop a dataset with 36k preference pairs based on human expert rankings, enhance multimodal large language models' perception of snowfall images using direct preference optimization (DPO), and refine desnowing models through a mean teacher semi-supervised framework with high-quality pseudo-label screening. This Framework substantially improves the generalization and performance of desnowing models on real snowfall images.