CFDNet: A Generalizable Foggy Stereo Matching Network with Contrastive Feature Distillation

TL;DR

CFDNet is a novel stereo matching network that uses contrastive feature distillation to improve depth estimation in foggy scenes, achieving better generalization across diverse environments.

Contribution

The paper introduces CFDNet, a new framework combining feature distillation and contrastive learning to enhance stereo matching in foggy conditions, surpassing previous methods.

Findings

Outperforms existing methods on synthetic and real datasets.

Improves robustness and generalization across foggy and clear scenes.

Effectively leverages fog cues without removing fog for depth estimation.

Abstract

Stereo matching under foggy scenes remains a challenging task since the scattering effect degrades the visibility and results in less distinctive features for dense correspondence matching. While some previous learning-based methods integrated a physical scattering function for simultaneous stereo-matching and dehazing, simply removing fog might not aid depth estimation because the fog itself can provide crucial depth cues. In this work, we introduce a framework based on contrastive feature distillation (CFD). This strategy combines feature distillation from merged clean-fog features with contrastive learning, ensuring balanced dependence on fog depth hints and clean matching features. This framework helps to enhance model generalization across both clean and foggy environments. Comprehensive experiments on synthetic and real-world datasets affirm the superior strength and adaptability of our method.