An advanced global point signature for 3D shape recognition and retrieval

Naffouti, Seif Eddine; Fougerolle, Yohan; Sakly, Anis; Mériaudeau, Fabrice

doi:10.1016/j.image.2017.07.005

Cited by 10 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recent discretization technique of the Laplacian Eigenspectrum made computational methods efficient and robust. The surface was modeled as a homogeneous vibrating membrane from spectral theory for shape analysis (see References [ 33 , 34 ]), and therefore Equation (2) in Reference [ 35 ] described its harmonic behavior. The powerful Spectral methods used for solving differential equations played a crucial role in object representation, due to the pose-invariant-property of the Laplace–Beltrami operator.…”

Section: Methodsmentioning

confidence: 99%

A Deep Learning Method for 3D Object Classification and Retrieval Using the Global Point Signature Plus and Deep Wide Residual Network

Long

Lee

Kwon

2021

Sensors

View full text Add to dashboard Cite

A vital and challenging task in computer vision is 3D Object Classification and Retrieval, with many practical applications such as an intelligent robot, autonomous driving, multimedia contents processing and retrieval, and augmented/mixed reality. Various deep learning methods were introduced for solving classification and retrieval problems of 3D objects. Almost all view-based methods use many views to handle spatial loss, although they perform the best among current techniques such as View-based, Voxelization, and Point Cloud methods. Many views make network structure more complicated due to the parallel Convolutional Neural Network (CNN). We propose a novel method that combines a Global Point Signature Plus with a Deep Wide Residual Network, namely GPSP-DWRN, in this paper. Global Point Signature Plus (GPSPlus) is a novel descriptor because it can capture more shape information of the 3D object for a single view. First, an original 3D model was converted into a colored one by applying GPSPlus. Then, a 32 × 32 × 3 matrix stored the obtained 2D projection of this color 3D model. This matrix was the input data of a Deep Residual Network, which used a single CNN structure. We evaluated the GPSP-DWRN for a retrieval task using the Shapnetcore55 dataset, while using two well-known datasets—ModelNet10 and ModelNet40 for a classification task. Based on our experimental results, our framework performed better than the state-of-the-art methods.

show abstract

Section: Methodsmentioning

confidence: 99%

A Deep Learning Method for 3D Object Classification and Retrieval Using the Global Point Signature Plus and Deep Wide Residual Network

Long

Lee

Kwon

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…It constitutes the foundations for geometric filtering or signal processing used in multi-resolution shape editing and mesh deformation. In recent years, mesh denoising has witnessed increasing demands in the computer graphics community [1], [2]. An important reason is that a large amount of original 3D data has emerged with the popularization of consumer-grade depth sensors and the various visual methods proposed for reconstructing 3D models [3]- [5].…”

Section: Introductionmentioning

confidence: 99%

Feature-Aware Trilateral Filter With Energy Minimization for 3D Mesh Denoising

2020

View full text Add to dashboard Cite

Sharp edges and corners are crucial features for high-quality and fine-detailed 3D meshes, which we tend to treat as noises in previous tasks of mesh denoising mistakenly. A challenge arises on how to handle both surfaces and features simultaneously in 3D mesh denoising. Classical works mainly focused on surfaces, whereas features also reasonably need proper processes. In this paper, we propose a feature-aware trilateral filter under the framework of energy minimization for 3D mesh denoising and address the above challenge. Concretely, we treat the challenge as an energy minimization model, where the data and smooth terms are both carefully designed. Apart from this, we introduce a feature-aware trilateral filter for high-quality mesh guidance to the model. In this filter, features are detected and distinguished from surfaces for consequent guidance. With the help of the model and filter, more priors are involved, and we can make global optimization for better denoising performance. We perform experiments on both synthetic and scanned meshes, where both subjective and objective evaluations are displayed to show the superior performance of our method to state-of-the-art methods. Furthermore, two experiments, including ablation tests and parameter sensitivities tests, are conducted to show the robustness and efficiency of our method thoroughly. All these results demonstrate that our method is suitable for robust and efficient performance in future mesh-oriented applications. INDEX TERMS Mesh denoising, feature-aware, multilateral filter, energy minimization.

show abstract