M${^2}$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zou, Yingshuang, Ding, Yikang, Qiu, Xi, Wang, Haoqian, Zhang, Haotian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913340133998592
author Zou, Yingshuang
Ding, Yikang
Qiu, Xi
Wang, Haoqian
Zhang, Haotian
author_facet Zou, Yingshuang
Ding, Yikang
Qiu, Xi
Wang, Haoqian
Zhang, Haotian
contents This paper presents a novel self-supervised two-frame multi-camera metric depth estimation network, termed M${^2}$Depth, which is designed to predict reliable scale-aware surrounding depth in autonomous driving. Unlike the previous works that use multi-view images from a single time-step or multiple time-step images from a single camera, M${^2}$Depth takes temporally adjacent two-frame images from multiple cameras as inputs and produces high-quality surrounding depth. We first construct cost volumes in spatial and temporal domains individually and propose a spatial-temporal fusion module that integrates the spatial-temporal information to yield a strong volume presentation. We additionally combine the neural prior from SAM features with internal features to reduce the ambiguity between foreground and background and strengthen the depth edges. Extensive experimental results on nuScenes and DDAD benchmarks show M${^2}$Depth achieves state-of-the-art performance. More results can be found in https://heiheishuang.xyz/M2Depth .
format Preprint
id arxiv_https___arxiv_org_abs_2405_02004
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle M${^2}$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation
Zou, Yingshuang
Ding, Yikang
Qiu, Xi
Wang, Haoqian
Zhang, Haotian
Computer Vision and Pattern Recognition
This paper presents a novel self-supervised two-frame multi-camera metric depth estimation network, termed M${^2}$Depth, which is designed to predict reliable scale-aware surrounding depth in autonomous driving. Unlike the previous works that use multi-view images from a single time-step or multiple time-step images from a single camera, M${^2}$Depth takes temporally adjacent two-frame images from multiple cameras as inputs and produces high-quality surrounding depth. We first construct cost volumes in spatial and temporal domains individually and propose a spatial-temporal fusion module that integrates the spatial-temporal information to yield a strong volume presentation. We additionally combine the neural prior from SAM features with internal features to reduce the ambiguity between foreground and background and strengthen the depth edges. Extensive experimental results on nuScenes and DDAD benchmarks show M${^2}$Depth achieves state-of-the-art performance. More results can be found in https://heiheishuang.xyz/M2Depth .
title M${^2}$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.02004