A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Large-Scale 3D Shape Retrieval from ShapeNet Core55
[article]
2016
Eurographics Workshop on 3D Object Retrieval, EG 3DOR
Preserved Fulltext
This track aims to provide a benchmark to evaluate large-scale shape retrieval based on the ShapeNet dataset. ...
We use ShapeNet Core55, which provides more than 50 thousands models over 55 common categories in total for training and evaluating several algorithms. ...
The covariance matrix lies not on the Euclidean space, but on the Riemannian manifold of symmetric positive semi-define matrices. ...
doi:10.2312/3dor.20161092
fatcat:6yoekzs7zfchnkztrmnicxy3cq
NPTC-net: Narrow-Band Parallel Transport Convolutional Neural Network on Point Clouds
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Designing appropriate convolution neural networks on manifold-structured point clouds can inherit and empower recent advances of CNNs to analyzing and processing point cloud data. ...
With that, we further propose a deep convolutional neural network based on NPTC (called NPTC-net) for point cloud classification and segmentation. ...
One of the main challenges of proposing geometric meaningful convolution on manifolds and point clouds (a discrete form of manifolds) is to define an analogy of the Euclidean translation x − y on the non-Euclidean ...
arXiv:1905.12218v3
fatcat:ogcgub3ebndgbmlpwab6sd4tkq
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
[chapter]
2018
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. ...
Experiments on ModelNet40 demonstrate that SpiderCNN achieves stateof-the-art accuracy 92.4% on standard benchmarks, and shows competitive performance on segmentation task. ...
Various studies are devoted to making convolution neural networks applicable for learning on non-Euclidean domains such as graphs or manifolds by trying to generalize the definition of convolution to functions ...
doi:10.1007/978-3-030-01237-3_6
fatcat:ewjesxzc5zcnrmdg42b7lhxjoa
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. ...
Experiments on ModelNet40 demonstrate that SpiderCNN achieves state-of-the-art accuracy 92.4% on standard benchmarks, and shows competitive performance on segmentation task. ...
Various studies are devoted to making convolution neural networks applicable for learning on non-Euclidean domains such as graphs or manifolds by trying to generalize the definition of convolution to functions ...
arXiv:1803.11527v3
fatcat:tsb3m6iamrconbyn3yfhs6l4rq
LaplacianNet: Learning on 3D Meshes with Laplacian Encoding and Pooling
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our network architecture is flexible enough to be used on meshes with different numbers of vertices. ...
We conduct several experiments including shape segmentation and classification, and our LaplacianNet outperforms state-of-the-art algorithms for these tasks on ShapeNet and COSEG datasets. ...
We therefore extend this ideology into non-Euclidean space of 2-manifolds. In our design as in Figure 1 , the basic network structure involves consecutive Mesh Pooling Blocks (MPBs). ...
arXiv:1910.14063v1
fatcat:sqzdkvvxrnerhaxzn3z2kpgkum
Geodesic-HOF: 3D Reconstruction Without Cutting Corners
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
on the object. ...
To address this issue, we propose learning an image-conditioned mapping function from a canonical sampling domain to a high dimensional space where the Euclidean distance is equal to the geodesic distance ...
With the success of Convolutional Neural Network (CNN) in processing image data, it is natural to extend it to 3D. ...
arXiv:2006.07981v1
fatcat:msyxgquzkjbx7fv77vawjkvaey
IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We provide a large-scale benchmark of classification and part segmentation by testing state-of-the-art networks. ...
Objects with arbitrary shapes are ubiquitous, and a non-Euclidean manifold reveals more critical information than using Euclidean geometry, like complex typologies of brain tissues in neuroscience [7] ...
The methods based on projected view or voxel are implemented conveniently using similar structures with 2D convolutional neural networks (CNNs). ...
arXiv:2003.02920v2
fatcat:ecsico6livgwpbmlqgjyuijvwe
3D Pick & Mix: Object Part Blending in Joint Shape and Image Manifolds
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Many applications could benefit from such rich queries, users could browse through catalogues of furniture and pick and mix parts, combining for example the legs of a chair from one shop and the armrests ...
The next step is to train a deep neural network that can map RGB images onto each manifold by regressing the coordinates on each part manifold directly from RGB inputs. ...
The Euclidean loss is chosen since the part shape manifolds are themselves Euclidean spaces. ...
arXiv:1811.01068v1
fatcat:ylj4bgefajfcxpluasszn7mgte
A Survey on Deep Geometry Learning: From a Representation Perspective
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Researchers have now achieved great success on dealing with 2D images using deep learning. In recent years, 3D computer vision and Geometry Deep Learning gain more and more attention. ...
However, the performance for different applications largely depends on the representation used, and there is no unique representation that works well for all applications. ...
Several works are designed in 2-manifolds with a series of refined CNN operators to adapt to this non-Euclidean space. ...
arXiv:2002.07995v2
fatcat:pustwlu5freypnccfrculkqvei
A-CNN: Annularly Convolutional Neural Networks on Point Clouds
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper presents a new method to define and compute convolution directly on 3D point clouds by the proposed annular convolution. ...
We apply it to the developed hierarchical neural networks for object classification, part segmentation, and semantic segmentation in large-scale scenes. ...
Meanwhile, several approaches have been proposed to develop convolutional networks on 2D manifolds [22, 4, 24, 41] . ...
arXiv:1904.08017v1
fatcat:itqbfcvjyzgtplapzpnr5m3we4
A survey on deep geometry learning: From a representation perspective
2020
Computational Visual Media
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The performance achieved in different applications largely depends on the representation used, and there is no unique representation that works well for all applications. ...
Several works have been designed using 2-manifolds with a series of refined CNN operators adapted to such non-Euclidean spaces. ...
One of the earliest methods to apply deep neural networks to volumetric representations, 3D ShapeNets, was proposed by Wu et al. [13] in 2015. ...
doi:10.1007/s41095-020-0174-8
fatcat:kpoynaixq5esbek63bovybisfa
Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We learn to predict this surrogate using a deep point cloud network and then feed it to an efficient post-processing module for high-quality mesh generation. ...
We demonstrate that our method can not only preserve details, handle ambiguous structures, but also possess strong generalizability to unseen categories by experiments on synthetic and real data. ...
Since meshes in ShapeNet are not manifolds, it's not trivial to calculate point normals with consistent directions, but many algorithms rely on correct normals. ...
arXiv:2007.09267v2
fatcat:onxslft3y5cojmz6mm57oo7xqi
Orientation-Encoding CNN for Point Cloud Classification and Segmentation
2021
Machine Learning and Knowledge Extraction
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
However, there are still tough challenges in applying them to convolutional neural networks due to the lack of a potential rule structure of point clouds. ...
Therefore, by taking the original point clouds as the input data, this paper proposes an orientation-encoding (OE) convolutional module and designs a convolutional neural network for effectively extracting ...
Spatial Domain The GeodesicCNN [17] is a generalization of the convolution network paradigm to non-Euclidean manifolds. ...
doi:10.3390/make3030031
fatcat:jj2jmeu42fhavgh5ebj5y2xyxq
Learning to Reconstruct Symmetric Shapes using Planar Parameterization of 3D Surface
2019
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This representation is encoded with surface information to generate 2D geometry images, which can be conveniently learned using traditional deep neural networks without additional overhead. ...
Prior knowledge encoded in trained networks has proven to be effective in generating images. Based on a similar paradigm, various methods were proposed to generate 3D shape from images. ...
Meshes not following Equation 1 are often referred to as non-manifold. These meshes have non-manifoldness in at least one of the vertices or edges. ...
doi:10.1109/iccvw.2019.00508
dblp:conf/iccvw/JainWH19
fatcat:c4t5osl2b5bkxdyzldh3xuhfpy
Faster Dynamic Graph CNN : Faster Deep Learning on 3D Point Cloud Data
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
A geodesic CNN (GCNN) [58] is a non-Euclidean deep learning algorithm that uses a spectral filter instead of a spatial filter. ...
, such as graphics and manifolds. ...
doi:10.1109/access.2020.3023423
fatcat:g3cvna7zp5eynpcsacbri52lve
« Previous
Showing results 1 — 15 out of 157 results