# A Two-Stage Adverse Weather Semantic Segmentation Method for WeatherProof Challenge CVPR 2024 Workshop UG2+

Source: [A Two-Stage Adverse Weather Semantic Segmentation Method for WeatherProof Challenge CVPR 2024 Workshop UG2+](<https://www.sota2.com/research/paper/68fa74131e209131cea5fab9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:02:03.292Z

Authors: Jianzhao Wang, Yanyan Wei, Dehua Hu, Yilin Zhang, Shengeng Tang, Kun Li, Zhao Zhang

Published: 2024-06-08T16:22:26.000Z

## Abstract

This technical report presents our team's solution for the WeatherProof Dataset Challenge: Semantic Segmentation in Adverse Weather at CVPR'24 UG2+. We propose a two-stage deep learning framework for this task. In the first stage, we preprocess the provided dataset by concatenating images into video sequences. Subsequently, we leverage a low-rank video deraining method to generate high-fidelity pseudo ground truths. These pseudo ground truths offer superior alignment compared to the original ground truths, facilitating model convergence during training. In the second stage, we employ the InternImage network to train for the semantic segmentation task using the generated pseudo ground truths. Notably, our meticulously designed framework demonstrates robustness to degraded data captured under adverse weather conditions. In the challenge, our solution achieved a competitive score of 0.43 on the Mean Intersection over Union (mIoU) metric, securing a respectable rank of 4th.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.05513>)

[PDF](<https://arxiv.org/pdf/2406.05513.pdf>)