Modelling and unsupervised learning of symmetric deformable object categories
We propose a new approach to model and learn, without manual supervision, the symmetries of natural objects, such as faces or flowers, given only images as input. It is well known that objects that have a symmetric structure do not usually result in symmetric images due to articulation and perspecti...
Main Authors: | Thewlis, J, Bilen, H, Vedaldi, A |
---|---|
Format: | Conference item |
Published: |
Neural Information Processing Systems
2018
|
Similar Items
-
Unsupervised learning of object landmarks by factorized spatial embeddings
by: Thewlis, J, et al.
Published: (2017) -
Unsupervised learning of object frames by dense equivariant image labelling
by: Thewlis, J, et al.
Published: (2017) -
Unsupervised learning of landmarks by descriptor vector exchange
by: Thewlis, J, et al.
Published: (2020) -
Unsupervised learning of probably symmetric deformable 3D objects from images in the wild
by: Wu, S, et al.
Published: (2020) -
Unsupervised learning of probably symmetric deformable 3D objects from images in the wild
by: Wu, S, et al.
Published: (2021)