Angelica Aviles-Rivero, Haoyu Chen, Yijun Yang, Lei Zhu, Jingjing Ren, Hongtao Wu, Sixiang Chen
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Snow degradations present formidable challenges to the advancement of computer vision tasks by the undesirable corruption in outdoor scenarios. While current deep learning-based desnowing approaches achieve success on synthetic benchmark datasets, they struggle to restore out-of-distribution real-world snowy videos due to the deficiency of paired real-world training data. To address this bottleneck, we devise a new paradigm for video desnowing in a semi-supervised spirit to involve unlabeled real data for the generalizable snow removal. Specifically, we construct a real-world dataset with 85 snowy videos, and then present a Semi-supervised Video Desnowing Network (SemiVDN) equipped by a novel Distribution-driven Contrastive Regularization. The elaborated contrastive regularization mitigates the distribution gap between the synthetic and real data, and consequently maintains the desired snowinvariant background details. Furthermore, based on the atmospheric scattering model, we introduce a Prior-guided Temporal Decoupling Experts module to decompose the physical components that make up a snowy video in a frame-correlated manner. We evaluate our SemiVDN on benchmark datasets and the collected real snowy data. The experimental results demonstrate the superiority of our approach against state-of-theart image-and video-level desnowing methods. Our code and the dataset are available at https://github.com/TonyHongtaoWu/SemiVDN.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.07901")
get_code_for_paper("2410.07901")
have("2410.07901")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2410.07901.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2410.07901)
Connect an agent — have() is free.