Other 1354 views
Consistent Segment-wise Matching with Multi-Layer Graphs
Taiwei Wang,
David George,
Yu-kun Lai,
Xianghua Xie 
,
Gary Tam
,
Gary Tam
International Conference on Geometric Modeling and Processing
Swansea University Author:
Xianghua Xie
Abstract
Segment-wise matching is an important research problem that supports higher-level understanding ofshapes in geometry processing. Many existing segment-wise matching techniques assume perfect input seg-mentation, and would suffer from imperfect or over-segmented input. To handle this shortcoming, we...
| Published in: | International Conference on Geometric Modeling and Processing |
|---|---|
| Published: |
|
| Online Access: |
http://www.eguk.org.uk/CGVC2018/programme.html |
| URI: | https://cronfa.swan.ac.uk/Record/cronfa49120 |
| Abstract: |
Segment-wise matching is an important research problem that supports higher-level understanding ofshapes in geometry processing. Many existing segment-wise matching techniques assume perfect input seg-mentation, and would suffer from imperfect or over-segmented input. To handle this shortcoming, we proposemulti-layer graphs (MLGs) to represent possible arrangements of partially merged segments of input shapes.We then adapt the diffusion pruning technique on the MLGs to find consistent segment-wise matching. Toobtain high quality matching, we develop a voting step to find hierarchically consistent correspondences asfinal output. We evaluate our technique with both qualitative and quantitative experiments on both man-made and deformable shapes. Experimental results demonstrate the effectiveness of our technique whencompared to two state-of-the-art methods. |
|---|---|
| College: |
Faculty of Science and Engineering |