Authors: Christopher Choy, Junha Lee, René Ranftl, Jaesik Park, Vladlen Koltun
Correspondences in 2D/3D forms geometric structures in higher dim, let's segment those with ND convnets!
#CVPR2020
![Image](https://pbs.twimg.com/media/Ea2DQYdUwAEtdmw.jpg)
Authors: Amir Hertz, Rana Hanocka, Raja Giryes, Daniel Cohen-Or
Constructing a hierarchical GMM by attentional split, and using the encoding for shape interpolation and generation.
#CVPR2020
![Image](https://pbs.twimg.com/media/Ea2Dxb4UcAE2Dia.jpg)
![Image](https://pbs.twimg.com/media/Ea2Dxb4UYAEhUQ4.jpg)
Keivan Alizadeh vahid, Anish Prabhu, Ali Farhadi, Mohammad Rastegari
Split data to K, combine ith element in each, recursively fuse in next layers, 1Dconv++!
(not distracted by "butterfly", no)
#CVPR2020
![Image](https://pbs.twimg.com/media/Ea2F53oUYAEzT67.jpg)
![Image](https://pbs.twimg.com/media/Ea2F53nVcAAlXzn.jpg)
Authors: Qinsong Li, Shengjun Liu, Ling Hu, Xinru Liu
Now you can apply anisotropic convolution to your pretty kittens using LB eigenspace + oriented spectral kernels!
#CVPR2020
![Image](https://pbs.twimg.com/media/Ea2HvUoU4AQ-fCZ.jpg)
Marvin Eisenberger, Zorah Lähner, Daniel Cremers
Shell operator = low freq geo (extrinsic). Embed shapes in extrinsic x spectral feature space, then matching = linear transformation and fmaps.
#CVPR2020
![Image](https://pbs.twimg.com/media/Ea2KQf3UEAEpSkV.jpg)
![Image](https://pbs.twimg.com/media/Ea2KQf4UwAImrjm.jpg)
![Image](https://pbs.twimg.com/media/Ea2KQf5U0AAvDXE.jpg)
![Image](https://pbs.twimg.com/media/Ea2KQf4VcAAshHf.jpg)
ipam.ucla.edu/wp-content/upl…
Non-CVPR.