A fast and efficient 3D reflection symmetry detector based on neural networks

Ji, Penglei; Liu, Xinguo

doi:10.1007/s11042-019-08043-9

Cited by 15 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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].…”

Section: Discussionmentioning

confidence: 99%

“…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].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Pramod

Arun

2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Achieving human-like visual abilities is a holy grail for machine vision, yet precisely how insights from human vision can improve machines has remained unclear. Here, we demonstrate two key conceptual advances: First, we show that most machine vision models are systematically different from human object perception. To do so, we collected a large dataset of perceptual distances between isolated objects in humans and asked whether these perceptual data can be predicted by many common machine vision algorithms. We found that while the best algorithms explain ∼70% of the variance in the perceptual data, all the algorithms we tested make systematic errors on several types of objects. In particular, machine algorithms underestimated distances between symmetric objects compared to human perception. Second, we show that fixing these systematic biases can lead to substantial gains in classification performance. In particular, augmenting a state-of-the-art convolutional neural network with planar/reflection symmetry scores along multiple axes produced significant improvements in classification accuracy (1-10%) across categories. These results show that machine vision can be improved by discovering and fixing systematic differences from human vision.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

Pramod

Arun

2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…They all require a rich training set and a relatively demanding and timeconsuming learning process. Ji and Liu [43] and Wu et al [44] address global reflection symmetries in point clouds, Gao et al [45] in voxel models, while Tsogkas and Kokkinos [46] deal with global and local reflection symmetries in raster images. Although these methods are promising, they are highly dependent on the learning datasets, which are not complete in all cases.…”

Section: Machine Learning In Symmetry Detectionmentioning

confidence: 99%

A Hierarchical Universal Algorithm for Geometric Objects’ Reflection Symmetry Detection

et al. 2022

View full text Add to dashboard Cite

A new algorithm is presented for detecting the global reflection symmetry of geometric objects. The algorithm works for 2D and 3D objects which may be open or closed and may or may not contain holes. The algorithm accepts a point cloud obtained by sampling the object’s surface at the input. The points are inserted into a uniform grid and so-called boundary cells are identified. The centroid of the boundary cells is determined, and a testing symmetry axis/plane is set through it. In this way, the boundary cells are split into two parts and they are faced with the symmetry estimation function. If the function estimates the symmetric case, the boundary cells are further split until a given threshold is reached or a non-symmetric result is obtained. The new testing axis/plane is then derived and tested by rotation around the centroid. This paper introduces three techniques to accelerate the computation. Competitive results were obtained when the algorithm was compared against the state of the art.

show abstract

“…Cicconet et al [22] regard the problem of finding planar symmetry as a problem of registering two datasets. Ji and Liu [23] propose a network to detect reflection symmetry, but their method needs supervised learning with annotated data. In contrast, our method is unsupervised, without requiring annotated data for training.…”

Section: Related Work 21 Symmetry Detectionmentioning

confidence: 99%

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

Gao

Zhang

Meng

et al. 2021

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

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.

show abstract

A fast and efficient 3D reflection symmetry detector based on neural networks

Cited by 15 publications

References 31 publications

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

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

A Hierarchical Universal Algorithm for Geometric Objects’ Reflection Symmetry Detection

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

Contact Info

Product

Resources

About