Capturing the geometry of object categories from video supervision
In this article, we are interested in capturing the 3D geometry of object categories simply by looking around them. Our unsupervised method fundamentally departs from traditional approaches that require either CAD models or manual supervision. It only uses video sequences capturing a handful of inst...
Main Authors: | Novotny, D, Larlus, D, Vedaldi, A |
---|---|
Format: | Journal article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers
2018
|
Similar Items
-
Learning the semantic structure of objects from Web supervision
by: Novotny, D, et al.
Published: (2016) -
Learning 3D object categories by looking around them
by: Novotny, D, et al.
Published: (2017) -
Learning the structure of object categories from incomplete supervision
by: Novotny, D
Published: (2018) -
AnchorNet: A weakly supervised network to learn geometry-sensitive features for semantic matching
by: Novotny, D, et al.
Published: (2017) -
I have seen enough: Transferring parts across categories
by: Novotny, D, et al.
Published: (2016)