arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.02004cs.CV
收藏

M${^2}$Depth:自监督双帧多相机度量深度估计

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

Tsinghua University(清华大学);Megvii Technology(旷视科技)

Yingshuang Zou, Yikang Ding, Xi Qiu, Haoqian Wang, Haotian Zhang

AI总结:

本文提出M${^2}$Depth,一种自监督双帧多相机度量深度估计网络,通过时空代价体融合与SAM神经先验增强边缘,在nuScenes和DDAD上达到最先进性能。

摘要:

本文提出了一种新颖的自监督双帧多相机度量深度估计网络,称为M${^2}$Depth,旨在自动驾驶中预测可靠的尺度感知的周围深度。与以往使用单一时间步的多视角图像或单一相机的多时间步图像的工作不同,M${^2}$Depth以来自多个相机的时间相邻双帧图像作为输入,并生成高质量的周围深度。我们首先分别在空间域和时间域构建代价体,并提出一个时空融合模块,该模块整合时空信息以产生强健的体积表示。此外,我们将来自SAM特征的神经先验与内部特征相结合,以减少前景与背景之间的歧义并增强深度边缘。在nuScenes和DDAD基准上的大量实验结果表明,M${^2}$Depth达到了最先进的性能。更多结果可在https://heiheishuang.xyz/M2Depth找到。

英文摘要:

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 .

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑