Paper Info
Title
3D2PM - 3d deformable part models
Abstract
As objects are inherently 3-dimensional, they have been modeled in 3D in the early days of computer vision. Due to the ambiguities arising from mapping 2D features to 3D models, 2D feature-based models are the predominant paradigm in object recognition today. While such models have shown competitive bounding box (BB) detection performance, they are clearly limited in their capability of fine-grained reasoning in 3D or continuous viewpoint estimation as required for advanced tasks such as 3D scene understanding. This work extends the deformable part model [1] to a 3D object model. It consists of multiple parts modeled in 3D and a continuous appearance model. As a result, the model generalizes beyond BB oriented object detection and can be jointly optimized in a discriminative fashion for object detection and viewpoint estimation. Our 3D Deformable Part Model (3D2PM) leverages on CAD data of the object class, as a 3D geometry proxy.
Year
DOI
Venue
2012
10.1007/978-3-642-33783-3_26
ECCV (6)
Keywords
Field
DocType
object recognition,object model,object detection,bb oriented object detection,feature-based model,continuous appearance model,deformable part model,object class,detection performance,model generalizes
CAD,Computer vision,Object detection,Computer science,Object model,Active appearance model,Object Class,Artificial intelligence,Discriminative model,Machine learning,Minimum bounding box,Cognitive neuroscience of visual object recognition
Conference
Citations 
PageRank 
References 
26
1.17
24
Authors
4
Name
Order
Citations
PageRank
Bojan Pepik1875.12
Peter Gehler2136361.64
Michael Stark373726.80
Bernt Schiele412901971.29