2017 IEEE International Conference on Image Processing (ICIP) 2017
DOI: 10.1109/icip.2017.8296956
|View full text |Cite
|
Sign up to set email alerts
|

Deep learning for 3D shape classification from multiple depth maps

Abstract: This paper proposes a novel approach for the classification of 3D shapes exploiting deep learning techniques. The proposed algorithm starts by constructing a set of depth maps by rendering the input 3D shape from different viewpoints. Then the depth maps are fed to a multi-branch Convolutional Neural Network. Each branch of the network takes in input one of the depth maps and produces a classification vector by using 5 convolutional layers of progressively reduced resolution. The various classification vectors… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
16
0

Year Published

2019
2019
2021
2021

Publication Types

Select...
9
1

Relationship

0
10

Authors

Journals

citations
Cited by 44 publications
(16 citation statements)
references
References 11 publications
0
16
0
Order By: Relevance
“…More research work to exploit multi-view 3D data was carried out. Zanuttigh and Minto in [121] used a multi-branch CNN to classify different 3D objects. In this work, the input consists of a rendered depth maps from different point of views of the 3D object and five convolutional layers for each CNN branch to process each depth maps to produce a class file vector.…”
Section: B Performance Of Deep Learning Methods On Multi-view Datamentioning
confidence: 99%
“…More research work to exploit multi-view 3D data was carried out. Zanuttigh and Minto in [121] used a multi-branch CNN to classify different 3D objects. In this work, the input consists of a rendered depth maps from different point of views of the 3D object and five convolutional layers for each CNN branch to process each depth maps to produce a class file vector.…”
Section: B Performance Of Deep Learning Methods On Multi-view Datamentioning
confidence: 99%
“…• Our method is consistently competitive compared with other representative view-based and model-based methods for both 3D model retrieval and classification tasks, which demonstrates the superiority and efficiency of our proposed method. [9] 77.0% -3D-GAN [27] 83.3% -VSL [28] 84.5% -Shape-based binVoxNetPlus [29] 85.47% -PointNet [30] 89.2% kd-Networks [31] 91.8% -3D-A-Nets [32] 90.5% 80.1% G3DNet [13] 91.13% -PointNet++ [33] 91.9% -DeepPano [34] 77.6% 76.8% GIFT [17] 83.1% 81.9% Geometry Image [35] 83.9% 53.1% View-based Multiple Depth Maps [36] 87.8% -MVCNN [18] 90.1% 79.5% PANORAMA-NN [37] 90.7% 83.5% Pariwise [38] 90.7% -MVCNN-MultiRes [39] 91.4% -MVTS (Our) 93.4% 87.3% • Previous view-based methods usually just select one representative view from the view sequence of the model, or employ simple view-level aggregation strategy, like the max-pooling (eg. MVCNN) method to fuse multiple views.…”
Section: A Comparison With the State-of-the-art Methodsmentioning
confidence: 99%
“…The RGBD benchmark dataset [20] has two issues for training multiview based CNNs: insufficient number of object instances per category (which is a minimum of two for training) and inconsistent cases to the upright orientation assumption. There are several cases where the upright orientation assumption is actually invalid; the attitudes of object instances against the rotation axis are inconsistent in some [39] 95.0 92.4 -MVCNN-MultiRes [27] 93.8 91.4 -Dominant Set Clustering [40] 93.8 --Kd-Networks [17] 91.8 -94.0 VRN-single [4] 91.33 -93.61 FusionNet [14] 90.80 -93.11 Pairwise [16] 90.70 -92.80 PANORAMA-NN [32] 90.7 -91.1 DeepSets [44] 90.3 --MVCNN [36] 90.10 90.10 -ORION [31] 89.7 -93.80 PointNet [26] 89.2 86.2 -LightNet [47] 88.93 -93.94 FPNN [22] 88.4 --Multiple Depth Maps [45] 87.8 -91.5 ECC [34] 87.4 83.2 90.8 VoxNet [23] 85.9 83.0 -3DShapeNets [42] 84.7 77.3 -Geometry Image [35] 83. We captured each object instance with M e ¼ 10 levels of elevation angles and 16 levels of azimuth angles to obtain 160 images.…”
Section: Experiments On a 3d Rotated Real Image Datasetmentioning
confidence: 99%