Abstract | ||
---|---|---|
We present a novel spatial hashing based data structure to facilitate 3D shape analysis using convolutional neural networks (CNNs). Our method builds hierarchical hash tables for an input model under different resolutions that leverage the sparse occupancy of 3D shape boundary. Based on this data structure, we design two efficient GPU algorithms namely hash2col and col2hash so that the CNN operati... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TVCG.2018.2887262 | IEEE Transactions on Visualization and Computer Graphics |
Keywords | Field | DocType |
Three-dimensional displays,Shape,Solid modeling,Convolution,Data structures,Two dimensional displays,Computational modeling | Data structure,Convolutional neural network,Convolution,Computer science,Algorithm,Theoretical computer science,Collision,Hash function,Memory footprint,Hash table,Shape analysis (digital geometry) | Journal |
Volume | Issue | ISSN |
26 | 7 | 1077-2626 |
Citations | PageRank | References |
0 | 0.34 | 34 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tianjia Shao | 1 | 293 | 17.59 |
Yin Yang | 2 | 116 | 18.48 |
Yanlin Weng | 3 | 492 | 15.36 |
Qiming Hou | 4 | 529 | 23.72 |
Kun Zhou | 5 | 3690 | 159.79 |