Identifying Style of 3D Shapes using Deep Metric Learning

We present a method that expands on previous work in learning human perceived style similarity across objects with different structures and functionalities. Unlike previous approaches that tackle this problem with the help of hand‐crafted geometric descriptors, we make use of recent advances in metr...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computer graphics forum Ročník 35; číslo 5; s. 207 - 215
Hlavní autoři: Lim, Isaak, Gehre, Anne, Kobbelt, Leif
Médium: Journal Article
Jazyk:angličtina
Vydáno: Oxford Blackwell Publishing Ltd 01.08.2016
Témata:
Analysis
Categories and Subject Descriptors (according to ACM CCS)
Classification
Collection
Computer graphics
deep metric learning
I.3.5 [Computer Graphics]: Computational Geometry and Object Modeling
Image processing systems
Learning
Neural networks
Similarity
State of the art
Studies
style similarity
Training
ISSN:0167-7055, 1467-8659
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We present a method that expands on previous work in learning human perceived style similarity across objects with different structures and functionalities. Unlike previous approaches that tackle this problem with the help of hand‐crafted geometric descriptors, we make use of recent advances in metric learning with neural networks (deep metric learning). This allows us to train the similarity metric on a shape collection directly, since any low‐ or high‐level features needed to discriminate between different styles are identified by the neural network automatically. Furthermore, we avoid the issue of finding and comparing sub‐elements of the shapes. We represent the shapes as rendered images and show how image tuples can be selected, generated and used efficiently for deep metric learning. We also tackle the problem of training our neural networks on relatively small datasets and show that we achieve style classification accuracy competitive with the state of the art. Finally, to reduce annotation effort we propose a method to incorporate heterogeneous data sources by adding annotated photos found online in order to expand or supplant parts of our training data.
Bibliografie:ark:/67375/WNG-QCKM3TVW-0
ArticleID:CGF12977
istex:4430CDB01F0FBD88144FDF867F8961CF2493E3B5
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.12977