English

Can Large Pretrained Depth Estimation Models Help With Image Dehazing?

Computer Vision and Pattern Recognition 2025-08-11 v2

Abstract

Image dehazing remains a challenging problem due to the spatially varying nature of haze in real-world scenes. While existing methods have demonstrated the promise of large-scale pretrained models for image dehazing, their architecture-specific designs hinder adaptability across diverse scenarios with different accuracy and efficiency requirements. In this work, we systematically investigate the generalization capability of pretrained depth representations-learned from millions of diverse images-for image dehazing. Our empirical analysis reveals that the learned deep depth features maintain remarkable consistency across varying haze levels. Building on this insight, we propose a plug-and-play RGB-D fusion module that seamlessly integrates with diverse dehazing architectures. Extensive experiments across multiple benchmarks validate both the effectiveness and broad applicability of our approach.

Keywords

Cite

@article{arxiv.2508.00698,
  title  = {Can Large Pretrained Depth Estimation Models Help With Image Dehazing?},
  author = {Hongfei Zhang and Kun Zhou and Ruizheng Wu and Jiangbo Lu},
  journal= {arXiv preprint arXiv:2508.00698},
  year   = {2025}
}
R2 v1 2026-07-01T04:29:34.359Z