Deep Learning of Local RGB-D Patches for 3D Object Detection and 6d Pose Estimation

Wadim Kehl, Fausto Milletari, Federico Tombari, Slobodan Ilic, Nassir Navab

ECCV 2016 pp. 205-220

doi:10.1007/978-3-319-46487-9_13 /eccv/2016/kehl2016eccv-deep/

Abstract

We present a 3D object detection method that uses regressed descriptors of locally-sampled RGB-D patches for 6D vote casting. For regression, we employ a convolutional auto-encoder that has been trained on a large collection of random local patches. During testing, scene patch descriptors are matched against a database of synthetic model view patches and cast 6D object votes which are subsequently filtered to refined hypotheses. We evaluate on three datasets to show that our method generalizes well to previously unseen input data, delivers robust detection results that compete with and surpass the state-of-the-art while being scalable in the number of objects.

PDF ECCV Semantic Scholar

Cite

Text

Kehl et al. "Deep Learning of Local RGB-D Patches for 3D Object Detection and 6d Pose Estimation." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46487-9_13

Markdown

[Kehl et al. "Deep Learning of Local RGB-D Patches for 3D Object Detection and 6d Pose Estimation." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/kehl2016eccv-deep/) doi:10.1007/978-3-319-46487-9_13

BibTeX

@inproceedings{kehl2016eccv-deep,
  title     = {{Deep Learning of Local RGB-D Patches for 3D Object Detection and 6d Pose Estimation}},
  author    = {Kehl, Wadim and Milletari, Fausto and Tombari, Federico and Ilic, Slobodan and Navab, Nassir},
  booktitle = {European Conference on Computer Vision},
  year      = {2016},
  pages     = {205-220},
  doi       = {10.1007/978-3-319-46487-9_13},
  url       = {https://mlanthology.org/eccv/2016/kehl2016eccv-deep/}
}