Adaptive Stereo Depth Estimation with Multi-Spectral Images Across All Lighting Conditions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Qin, Zihan, Xu, Jialei, Zhao, Wenbo, Jiang, Junjun, Liu, Xianming
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912106942562304
author Qin, Zihan
Xu, Jialei
Zhao, Wenbo
Jiang, Junjun
Liu, Xianming
author_facet Qin, Zihan
Xu, Jialei
Zhao, Wenbo
Jiang, Junjun
Liu, Xianming
contents Depth estimation under adverse conditions remains a significant challenge. Recently, multi-spectral depth estimation, which integrates both visible light and thermal images, has shown promise in addressing this issue. However, existing algorithms struggle with precise pixel-level feature matching, limiting their ability to fully exploit geometric constraints across different spectra. To address this, we propose a novel framework incorporating stereo depth estimation to enforce accurate geometric constraints. In particular, we treat the visible light and thermal images as a stereo pair and utilize a Cross-modal Feature Matching (CFM) Module to construct a cost volume for pixel-level matching. To mitigate the effects of poor lighting on stereo matching, we introduce Degradation Masking, which leverages robust monocular thermal depth estimation in degraded regions. Our method achieves state-of-the-art (SOTA) performance on the Multi-Spectral Stereo (MS2) dataset, with qualitative evaluations demonstrating high-quality depth maps under varying lighting conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2411_03638
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive Stereo Depth Estimation with Multi-Spectral Images Across All Lighting Conditions
Qin, Zihan
Xu, Jialei
Zhao, Wenbo
Jiang, Junjun
Liu, Xianming
Computer Vision and Pattern Recognition
Artificial Intelligence
Depth estimation under adverse conditions remains a significant challenge. Recently, multi-spectral depth estimation, which integrates both visible light and thermal images, has shown promise in addressing this issue. However, existing algorithms struggle with precise pixel-level feature matching, limiting their ability to fully exploit geometric constraints across different spectra. To address this, we propose a novel framework incorporating stereo depth estimation to enforce accurate geometric constraints. In particular, we treat the visible light and thermal images as a stereo pair and utilize a Cross-modal Feature Matching (CFM) Module to construct a cost volume for pixel-level matching. To mitigate the effects of poor lighting on stereo matching, we introduce Degradation Masking, which leverages robust monocular thermal depth estimation in degraded regions. Our method achieves state-of-the-art (SOTA) performance on the Multi-Spectral Stereo (MS2) dataset, with qualitative evaluations demonstrating high-quality depth maps under varying lighting conditions.
title Adaptive Stereo Depth Estimation with Multi-Spectral Images Across All Lighting Conditions
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2411.03638