MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo Matching

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Feng, Miaojie, Cheng, Junda, Jia, Hao, Liu, Longliang, Xu, Gangwei, Hu, Qingyong, Yang, Xin
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917576569782272
author Feng, Miaojie
Cheng, Junda
Jia, Hao
Liu, Longliang
Xu, Gangwei
Hu, Qingyong
Yang, Xin
author_facet Feng, Miaojie
Cheng, Junda
Jia, Hao
Liu, Longliang
Xu, Gangwei
Hu, Qingyong
Yang, Xin
contents Stereo matching is a fundamental task in scene comprehension. In recent years, the method based on iterative optimization has shown promise in stereo matching. However, the current iteration framework employs a single-peak lookup, which struggles to handle the multi-peak problem effectively. Additionally, the fixed search range used during the iteration process limits the final convergence effects. To address these issues, we present a novel iterative optimization architecture called MC-Stereo. This architecture mitigates the multi-peak distribution problem in matching through the multi-peak lookup strategy, and integrates the coarse-to-fine concept into the iterative framework via the cascade search range. Furthermore, given that feature representation learning is crucial for successful learn-based stereo matching, we introduce a pre-trained network to serve as the feature extractor, enhancing the front end of the stereo matching pipeline. Based on these improvements, MC-Stereo ranks first among all publicly available methods on the KITTI-2012 and KITTI-2015 benchmarks, and also achieves state-of-the-art performance on ETH3D. Code is available at https://github.com/MiaoJieF/MC-Stereo.
format Preprint
id arxiv_https___arxiv_org_abs_2311_02340
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo Matching
Feng, Miaojie
Cheng, Junda
Jia, Hao
Liu, Longliang
Xu, Gangwei
Hu, Qingyong
Yang, Xin
Computer Vision and Pattern Recognition
Stereo matching is a fundamental task in scene comprehension. In recent years, the method based on iterative optimization has shown promise in stereo matching. However, the current iteration framework employs a single-peak lookup, which struggles to handle the multi-peak problem effectively. Additionally, the fixed search range used during the iteration process limits the final convergence effects. To address these issues, we present a novel iterative optimization architecture called MC-Stereo. This architecture mitigates the multi-peak distribution problem in matching through the multi-peak lookup strategy, and integrates the coarse-to-fine concept into the iterative framework via the cascade search range. Furthermore, given that feature representation learning is crucial for successful learn-based stereo matching, we introduce a pre-trained network to serve as the feature extractor, enhancing the front end of the stereo matching pipeline. Based on these improvements, MC-Stereo ranks first among all publicly available methods on the KITTI-2012 and KITTI-2015 benchmarks, and also achieves state-of-the-art performance on ETH3D. Code is available at https://github.com/MiaoJieF/MC-Stereo.
title MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo Matching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.02340