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 (3D^2PM) leverages on CAD data of the object class, as a 3D geometry proxy.
Cite
Text
Pepik et al. "3D2PM - 3D Deformable Part Models." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33783-3_26Markdown
[Pepik et al. "3D2PM - 3D Deformable Part Models." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/pepik2012eccv-d/) doi:10.1007/978-3-642-33783-3_26BibTeX
@inproceedings{pepik2012eccv-d,
title = {{3D2PM - 3D Deformable Part Models}},
author = {Pepik, Bojan and Gehler, Peter V. and Stark, Michael and Schiele, Bernt},
booktitle = {European Conference on Computer Vision},
year = {2012},
pages = {356-370},
doi = {10.1007/978-3-642-33783-3_26},
url = {https://mlanthology.org/eccv/2012/pepik2012eccv-d/}
}