A repeatable and robust local reference frame for 3D surface matching

Ao, Sheng; Guo, Yulan; Tian, Jing; Tian, Yong; Li, Dong

doi:10.1016/j.patcog.2019.107186

Cited by 13 publications

(16 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To realize the rotation invariance, we propose a simplified local reference frame (LRF) for the patches, i.e., SLRF. We define the coordinate system of original point clouds as global reference frame, while LRF is a local coordinate system (with three orthogonal axes) built on a local patch surface, which is considered as repeatable under rigid rotations [44], [45], [46]. We rotate the patches to a fixed position by the rotation matrix between SLRF and global reference frame.…”

Section: Coordinate Normalizationmentioning

confidence: 99%

GPA-Net:No-Reference Point Cloud Quality Assessment with Multi-task Graph Convolutional Network

Ziyu¹,

Yang²,

Rui³

et al. 2022

Preprint

View full text Add to dashboard Cite

With the rapid development of 3D vision, point cloud has become an increasingly popular 3D visual media content. Due to the irregular structure, point cloud has posed novel challenges to the related research, such as compression, transmission, rendering and quality assessment. In these latest researches, point cloud quality assessment (PCQA) has attracted wide attention due to its significant role in guiding practical applications, especially in many cases where the reference point cloud is unavailable. However, current no-reference metrics which based on prevalent deep neural network have apparent disadvantages. For example, to adapt to the irregular structure of point cloud, they require preprocessing such as voxelization and projection that introduce extra distortions, and the applied grid-kernel networks, such as Convolutional Neural Networks, fail to extract effective distortion-related features. Besides, they rarely consider the various distortion patterns and the philosophy that PCQA should exhibit shifting, scaling, and rotational invariance. In this paper, we propose a novel no-reference PCQA metric named the Graph convolutional PCQA network (GPA-Net). To extract effective features for PCQA, we propose a new graph convolution kernel, i.e., GPAConv, which attentively captures the perturbation of structure and texture. Then, we propose the multi-task framework consisting of one main task (quality regression) and two auxiliary tasks (distortion type and degree predictions). Finally, we propose a coordinate normalization module to stabilize the results of GPAConv under shift, scale and rotation transformations. Experimental results on two independent databases show that GPA-Net achieves the best performance compared to the state-of-the-art no-reference PCQA metrics, even better than some full-reference metrics in some cases. The code is available at: https://github.com/Slowhander/GPA-Net.git

show abstract

Section: Coordinate Normalizationmentioning

confidence: 99%

GPA-Net:No-Reference Point Cloud Quality Assessment with Multi-task Graph Convolutional Network

Ziyu¹,

Yang²,

Rui³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Alignment with a Reference Axis. Given a specific point p ∈ P in a local surface, we first estimate a reference axis n p oriented to the viewpoint [38,1] from its neighbouring point set P s = {p i : p i − p 2 ≤ R} within a support radius R. We then align n p with the Z-axis using a rotation matrix R z . Compared with the external local reference frames which are likely to be ambiguous and unstable, our estimated n p tends to be more robust and stable with regard to rotation changes [42].…”

Section: Spatial Point Transformermentioning

confidence: 99%

SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration

Ao¹,

Yang

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Extracting robust and general 3D local features is key to downstream tasks such as point cloud registration and reconstruction. Existing learning-based local descriptors are either sensitive to rotation transformations, or rely on classical handcrafted features which are neither general nor representative. In this paper, we introduce a new, yet conceptually simple, neural architecture, termed SpinNet, to extract local features which are rotationally invariant whilst sufficiently informative to enable accurate registration. A Spatial Point Transformer is first introduced to map the input local surface into a carefully designed cylindrical space, enabling end-to-end optimization with SO(2) equivariant representation. A Neural Feature Extractor which leverages the powerful point-based and 3D cylindrical convolutional neural layers is then utilized to derive a compact and representative descriptor for matching. Extensive experiments on both indoor and outdoor datasets demonstrate that SpinNet outperforms existing state-of-theart techniques by a large margin. More critically, it has the best generalization ability across unseen scenarios with different sensor modalities. The code is available at https: //github.com/QingyongHu/SpinNet.

show abstract

“…Other methods use geometric features (GA-Based) [ 28 ] to estimate the LRF, including the point position, normal, curvature, projection height, and gradient. In particular, Ao [ 29 ] is an LRF estimation method used for CA-Based and GA-Based (Mix-Based). From the definition of the X-axis, Ao [ 29 ] uses the height information to remap the projected point cloud, which is consistent with the definition of the GA method.…”

Section: Introductionmentioning

confidence: 99%

“…In particular, Ao [ 29 ] is an LRF estimation method used for CA-Based and GA-Based (Mix-Based). From the definition of the X-axis, Ao [ 29 ] uses the height information to remap the projected point cloud, which is consistent with the definition of the GA method. Compared with the CA-Based method, the GA-Based method and Mix-Based method are more robust in complex scenarios as they calculate the X-axis separately.…”

Section: Introductionmentioning

confidence: 99%

“…Compared with the CA-Based method, the GA-Based method and Mix-Based method are more robust in complex scenarios as they calculate the X-axis separately. In addition, the robustness of the Z-axis can be improved by selecting a suitable support radius [ 29 , 30 ]. Therefore, the robustness of LRFs is largely limited by the estimated X-axis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SliceLRF: A Local Reference Frame Sliced along the Height on the 3D Surface

Zhong

Liu

2023

Sensors

Self Cite

View full text Add to dashboard Cite

The local reference frame (LRF) plays a vital role in local 3D shape description and matching. Numerous LRF methods have been proposed in recent decades. However, few LRFs can achieve a balance between repeatability and robustness under exposure to a variety of nuisances, including Gaussian noise, mesh resolution variation, clutter, and occlusion. Additionally, most LRFs are heuristic and lack generalizability to different applications and data modalities. In this paper, we first define the degree of distinction to describe the distribution of 2D point clouds and explore the relationship between the relative deviation of the distinction degree and the LRF error through experiments. Based on Gaussian noise and a random sampling analysis, several factors that affect the relative deviation of the distinction degree and result in the LRF error are identified. A scoring criterion is proposed to evaluate the robustness of the point cloud distribution. On this basis, we propose an LRF method (SliceLRF) based on slicing along the Z-axis, which selects the most robust adjacent slices in the point cloud region by scoring criteria for X-axis estimation to improve the repeatability and robustness. SliceLRF is rigorously tested on four public benchmark datasets which have different applications and involve different data modalities. It is also compared with the state-of-the-art LRFs. The experimental results show that the SliceLRF has more comprehensive repeatability and robustness than the other LRFs under exposure to Gaussian noise and random sampling.

show abstract

A repeatable and robust local reference frame for 3D surface matching

Cited by 13 publications

References 28 publications

GPA-Net:No-Reference Point Cloud Quality Assessment with Multi-task Graph Convolutional Network

GPA-Net:No-Reference Point Cloud Quality Assessment with Multi-task Graph Convolutional Network

SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration

SliceLRF: A Local Reference Frame Sliced along the Height on the 3D Surface

Contact Info

Product

Resources

About