arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.19166cs.CV
收藏

重新审视基于局部运动恢复结构的自监督深度估计

Revisit Self-supervised Depth Estimation with Local Structure-from-Motion

Michigan State University(密歇根州立大学)

Shengjie Zhu, Xiaoming Liu

AI总结:

本文提出用局部SfM替代传统损失驱动的自监督深度估计,通过bundle-RANSAC-adjustment联合优化位姿与深度调整,并用无神经网络NeRF进行稠密三角化,首次证明5帧内自监督即可提升SoTA监督模型性能。

摘要:

自监督深度估计和运动恢复结构(SfM)都从RGB视频中恢复场景深度。尽管目标相似,这两种方法却是脱节的。先前自监督工作反向传播在直接相邻帧内定义的损失。本工作不采用通过损失学习的方式,而是提出一种替代方案,通过执行局部SfM来实现。首先,利用已标定的RGB或RGB-D图像,我们使用深度和对应关系估计器来推断深度图和成对对应关系图。然后,一种新颖的bundle-RANSAC-adjustment算法联合优化相机位姿以及每个深度图的一个深度调整量。最后,我们固定相机位姿并使用NeRF,但不含神经网络,进行稠密三角化和几何验证。位姿、深度调整量和三角化稀疏深度是我们的输出。我们首次证明,在5帧内进行自监督已经能使最先进的监督式深度和对应关系模型受益。项目主页位于链接(https://shngjz.github.io/SSfM.github.io/)。

英文摘要:

Both self-supervised depth estimation and Structure-from-Motion (SfM) recover scene depth from RGB videos. Despite sharing a similar objective, the two approaches are disconnected. Prior works of self-supervision backpropagate losses defined within immediate neighboring frames. Instead of learning-through-loss, this work proposes an alternative scheme by performing local SfM. First, with calibrated RGB or RGB-D images, we employ a depth and correspondence estimator to infer depthmaps and pair-wise correspondence maps. Then, a novel bundle-RANSAC-adjustment algorithm jointly optimizes camera poses and one depth adjustment for each depthmap. Finally, we fix camera poses and employ a NeRF, however, without a neural network, for dense triangulation and geometric verification. Poses, depth adjustments, and triangulated sparse depths are our outputs. For the first time, we show self-supervision within $5$ frames already benefits SoTA supervised depth and correspondence models. The project page is held in the link (https://shngjz.github.io/SSfM.github.io/).

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。

↑