Abstract | ||
---|---|---|
Convolutional neural networks have been successfully used to compute shape descriptors, or jointly embed shapes and sketches in a common vector space. We propose a novel approach that leverages both labeled 3D shapes and semantic information contained in the labels, to generate semantically-meaningful shape descriptors. A neural network is trained to generate shape descriptors that lie close to a vector representation of the shape class, given a vector space of words. This method is easily extendable to range scans, hand-drawn sketches and images. This makes cross-modal retrieval possible, without a need to design different methods depending on the query type. We show that sketch-based shape retrieval using semantic-based descriptors outperforms the state-of-the-art by large margins, and mesh-based retrieval generates results of higher relevance to the query, than current deep shape descriptors. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1145/2980179.2980253 | ACM Trans. Graph. |
Keywords | Field | DocType |
shape descriptor,word vector space,semantic-based,depthmap,2D sketch,deep learning,CNN | Computer vision,Vector space,Pattern recognition,Computer science,Convolutional neural network,3d shapes,Semantic information,Artificial intelligence,Deep learning,Artificial neural network | Journal |
Volume | Issue | ISSN |
35 | 6 | 0730-0301 |
Citations | PageRank | References |
12 | 0.56 | 21 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Flora Ponjou Tasse | 1 | 53 | 4.41 |
Neil A. Dodgson | 2 | 723 | 54.20 |