User: Guest  Login
Document type:
Konferenzbeitrag
Author(s):
Deng, H.; Birdal, T.; Ilic, S.
Title:
PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors
Abstract:
We present PPF-FoldNet for unsupervised learning of 3D local descriptors on pure point cloud geometry. Based on the folding-based auto-encoding of well known point pair features, PPF-FoldNet offers many desirable properties: it necessitates neither supervision, nor a sensitive local reference frame, benefits from point-set sparsity, is end-to-end, fast, and can extract powerful rotation invariant descriptors. Thanks to a novel feature visualization, its evolution can be monitored to provide inte...     »
Keywords:
CAMP,CAMPComputerVision,ComputerVision,Rigid3DObjectDetection,ProjectPointClouds,ECCV,ECCV2018,Reconstruction,3DReconstruction
Book / Congress title:
European Conference on Computer Vision (ECCV)
Organization:
Springer
Year:
2018
 BibTeX