arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.10042cs.CVcs.LG
收藏

学习检测单视图重建的3D反射对称性

Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction

Univ. of California, Berkeley(加州大学伯克利分校);Univ. of Southern California(南加州大学)

Yichao Zhou, Shichen Liu, Yi Ma

摘要:

从一幅RGB图像进行三维重建是计算机视觉中一个具有挑战性的问题。以前的方法通常是完全数据驱动的,这导致不准确的3D形状恢复和有限的泛化能力。在这项工作中,我们专注于对象级3D重建,并提出了一个基于几何的端到端深度学习框架,该框架首先检测通常存在于人造对象中的反射对称的镜像平面,然后通过找到对称的图像内像素对应来预测深度图。我们的方法充分利用了几何线索,从对称性在测试时间内,通过建立平面扫描成本卷,一个强大的工具,已被用于多视图立体视觉。据我们所知,这是第一个工作,使用的概念,成本量在单图像三维重建的设置。我们对ShapeNet数据集进行了广泛的实验,发现我们的重建方法在相机姿态和深度图的准确性方面显着优于以前最先进的单视图3D重建网络,而不需要对象完全对称。代码可在https://github.com/zhou13/symmetrynet上获得。

英文摘要:

3D reconstruction from a single RGB image is a challenging problem in computer vision. Previous methods are usually solely data-driven, which lead to inaccurate 3D shape recovery and limited generalization capability. In this work, we focus on object-level 3D reconstruction and present a geometry-based end-to-end deep learning framework that first detects the mirror plane of reflection symmetry that commonly exists in man-made objects and then predicts depth maps by finding the intra-image pixel-wise correspondence of the symmetry. Our method fully utilizes the geometric cues from symmetry during the test time by building plane-sweep cost volumes, a powerful tool that has been used in multi-view stereopsis. To our knowledge, this is the first work that uses the concept of cost volumes in the setting of single-image 3D reconstruction. We conduct extensive experiments on the ShapeNet dataset and find that our reconstruction method significantly outperforms the previous state-of-the-art single-view 3D reconstruction networks in term of the accuracy of camera poses and depth maps, without requiring objects being completely symmetric. Code is available at https://github.com/zhou13/symmetrynet.

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。

↑