|国家预印本平台
首页|Can Large Pretrained Depth Estimation Models Help With Image Dehazing?

Can Large Pretrained Depth Estimation Models Help With Image Dehazing?

Can Large Pretrained Depth Estimation Models Help With Image Dehazing?

来源:Arxiv_logoArxiv
英文摘要

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.

Hongfei Zhang、Kun Zhou、Ruizheng Wu、Jiangbo Lu

光电子技术微电子学、集成电路电子技术应用

Hongfei Zhang,Kun Zhou,Ruizheng Wu,Jiangbo Lu.Can Large Pretrained Depth Estimation Models Help With Image Dehazing?[EB/OL].(2025-08-08)[2025-08-19].https://arxiv.org/abs/2508.00698.点此复制

评论