Name
Abstract | ||
|---|---|---|
Object part segmentation is a challenging and fundamental problem in computer vision. Its difficulties may be caused by the varying viewpoints, poses, and topological structures, which can be attributed to an essential reason, i.e., a specific object is a 3D model rather than a 2D figure. Therefore, we conjecture that not only 2D appearance features but also 3D geometric features could be helpful. With this in mind, we propose a 2-stream FCN. One stream, named AppNet, is to extract 2D appearance features from the input image. The other stream, named GeoNet, is to extract 3D geometric features. However, the problem is that the input is just an image. To this end, we design a 2D convolution based CNN structure to extract 3D geometric features from 3D volume, which is named VolNet. Then a teacher-student strategy is adopted and VolNet teaches GeoNet how to extract 3D geometric features from an image. To perform this teaching process, we synthesize training data using 3D models. Each training sample consists of an image and its corresponding volume. A perspective voxelization algorithm is further proposed to align them. Experimental results verify our conjecture and the effectiveness of both the proposed 2-stream CNN and VolNet. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1109/ICCV.2017.70 | 2017 IEEE International Conference on Computer Vision (ICCV) |
Keywords | Field | DocType |
embedding 3D geometric features,rigid object part segmentation,2D appearance features,2-stream FCN,2-stream CNN,2D convolution based CNN structure,VolNet,teaching process,perspective voxelization algorithm | Computer vision,Embedding,Pattern recognition,Segmentation,Computer science,Viewpoints,Feature extraction,Image segmentation,Artificial intelligence,Solid modeling,Conjecture,Semantics | Conference |
Volume | Issue | ISSN |
2017 | 1 | 1550-5499 |
ISBN | Citations | PageRank |
978-1-5386-1033-6 | 0 | 0.34 |
References | Authors | |
17 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yafei Song | 1 | 36 | 5.63 |
| Xiaowu Chen | 2 | 605 | 45.05 |
| Jia Li | 3 | 524 | 42.09 |
| Qinping Zhao | 4 | 363 | 43.20 |