PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models

Abstract

In geometry processing, symmetry is a universal type of high-level structural information of 3D models and benefits many geometry processing tasks including shape segmentation, alignment, matching, and completion. Thus it is an important problem to analyze various symmetry forms of 3D shapes. Planar reflective symmetry is the most fundamental one. Traditional methods based on spatial sampling can be time-consuming and may not be able to identify all the symmetry planes. In this paper, we present a novel learning framework to automatically discover global planar reflective symmetry of a 3D shape. Our framework trains an unsupervised 3D convolutional neural network to extract global model features and then outputs possible global symmetry parameters, where input shapes are represented using voxels. We introduce a dedicated symmetry distance loss along with a regularization loss to avoid generating duplicated symmetry planes. Our network can also identify generalized cylinders by predicting their rotation axes. We further provide a method to remove invalid and duplicated planes and axes. We demonstrate that our method is able to produce reliable and accurate results. Our neural network based method is hundreds of times faster than the state-of-the-art methods, which are based on sampling. Our method is also robust even with noisy or incomplete input surfaces.

Improving Machine Vision Using Human Perceptual Representations: The Case of Planar Reflection Symmetry for Object Classification

“…Our improvements in performance may have been small due to noisy estimates of symmetry features. Recent advances in geometry processing using classical methods as well as deep learning have led to better symmetry detectors both on 3D models of objects [25], [29], [31] and 2D objects embedded in natural scenes [26], [30]. Further, there have been efforts to reduce the sample complexity of deep neural networks by designing convolutional filters that capture various symmetries in the training data [27], [28].…”

“…Symmetry is an important property in our perception [9], [10], [23] that we detect far better than machine algorithms [24]. Symmetry detection in an image is a challenging problem that has been studied extensively [24], [25], [26] including more recently using neural networks [27], [28], [29], [30], [31]. Recent studies have suggested a role for local ribbon symmetry in contours in scene categorization [32].…”

A survey on deep geometry learning: From a representation perspective

“…Reproduced with permission from Ref. [120]. we discuss 3D shape applications based on different 3D representations, including shape analysis and shape reconstruction.…”

“…Symmetry is important in 3D shapes, and can be further used in many other applications such as shape alignment, registration, completion, etc. Gao et al [120] designed the first unsupervised deep learning method, PRS-Net (planar reflective symmetry net), to detect planar reflective symmetry in 3D shapes, using a new symmetry distance loss and a regularization loss, as illustrated in Fig. 6.…”

Symmetry Detection and Analysis of Chinese Paifang Using 3D Point Clouds

“…For computation of the symmetry using machine learning approaches, Gao et al developed a convolutional neural network (CNN) to estimate the plane of symmetry of a set of objects including tables, cabinets and boats [10]. The CNN required training data to input into the model.…”