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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Zihua, Li, Yizhou, Okutomi, Masatoshi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913255965851648
author Liu, Zihua
Li, Yizhou
Okutomi, Masatoshi
author_facet Liu, Zihua
Li, Yizhou
Okutomi, Masatoshi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18181
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CFDNet: A Generalizable Foggy Stereo Matching Network with Contrastive Feature Distillation
Liu, Zihua
Li, Yizhou
Okutomi, Masatoshi
Computer Vision and Pattern Recognition
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.
title CFDNet: A Generalizable Foggy Stereo Matching Network with Contrastive Feature Distillation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.18181