NeuroMorph: unsupervised shape interpolation and correspondence in one go
We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes and produces in one go, i.e. in a single feed forward pass, a smooth interpolation and point-to-point correspondences between them. The interpolation, expressed as a deformation field, changes the pose of the...
Үндсэн зохиолчид: | Eisenberger, M, Novotny, D, Kerchenbaum, G, Labatut, P, Neverova, N, Cremers, D, Vedaldi, A |
---|---|
Формат: | Conference item |
Хэл сонгох: | English |
Хэвлэсэн: |
IEEE
2021
|
Ижил төстэй зүйлс
Ижил төстэй зүйлс
-
Correlated uncertainty for learning dense correspondences from noisy labels
-н: Neverova, N, зэрэг
Хэвлэсэн: (2019) -
Unsupervised learning of 3D object categories from videos in the wild
-н: Henzler, P, зэрэг
Хэвлэсэн: (2021) -
Discovering relationships between object categories via universal canonical maps
-н: Neverova, N, зэрэг
Хэвлэсэн: (2021) -
Low-power neuromorphic circuits for unsupervised spike based learning
-н: He, Tong
Хэвлэсэн: (2016) -
Shape morphing of plastic films
-н: Zhang, Feilong, зэрэг
Хэвлэсэн: (2023)