• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Improved Sliding Shapes for Instance Segmentation of Amodal 3D Object

Vol. 12, No.11, November 30, 2018
10.3837/tiis.2018.11.021, Download Paper (Free):

Abstract

State-of-art instance segmentation networks are successful at generating 2D segmentation mask for region proposals with highest classification score, yet 3D object segmentation task is limited to geocentric embedding or detector of Sliding Shapes. To this end, we propose an amodal 3D instance segmentation network called A3IS-CNN, which extends the detector of Deep Sliding Shapes to amodal 3D instance segmentation by adding a new branch of 3D ConvNet called A3IS-branch. The A3IS-branch which takes 3D amodal ROI as input and 3D semantic instances as output is a fully convolution network(FCN) sharing convolutional layers with existing 3d RPN which takes 3D scene as input and 3D amodal proposals as output. For two branches share computation with each other, our 3D instance segmentation network adds only a small overhead of 0.25 fps to Deep Sliding Shapes, trading off accurate detection and point-to-point segmentation of instances. Experiments show that our 3D instance segmentation network achieves at least 10% to 50% improvement over the state-of-art network in running time, and outperforms the state-of-art 3D detectors by at least 16.1 AP.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
Jinhua Lin, Yu Yao and Yanjie Wang, "Improved Sliding Shapes for Instance Segmentation of Amodal 3D Object," KSII Transactions on Internet and Information Systems, vol. 12, no. 11, pp. 5555-5567, 2018. DOI: 10.3837/tiis.2018.11.021

[ACM Style]
Lin, J., Yao, Y., and Wang, Y. 2018. Improved Sliding Shapes for Instance Segmentation of Amodal 3D Object. KSII Transactions on Internet and Information Systems, 12, 11, (2018), 5555-5567. DOI: 10.3837/tiis.2018.11.021