论文标题
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
论文作者
论文摘要
来自单个RGB图像的3D重建是计算机视觉中的一个具有挑战性的问题。以前的方法通常仅是数据驱动的，这导致3D形状恢复和有限的概括能力不准确。在这项工作中，我们专注于对象级3D重建，并提出一个基于几何的端到端深度学习框架，该框架首先检测到反射对称的镜面平面，该镜面通常存在于人造物体中，然后通过找到对称性的对象内图像对象来预测深度图。我们的方法通过构建平面扫描成本量，在测试时间内完全利用了对称性的几何提示，这是一种强大的工具，该工具已在多视图立体访问中使用。据我们所知，这是在单像3D重建的设置中使用成本量概念的第一部作品。我们在Shapenet数据集上进行了广泛的实验，并发现我们的重建方法在相机姿势和深度图的准确性方面显着超过了先前最新的单视3D 3D重建网络，而无需对象完全对称。代码可在https://github.com/zhou13/symmetrynet上找到。
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.
