Page of Filippos Kokkinos
Page of Filippos Kokkinos
Home
Posts
Projects
Publications
Contact
CV
Light
Dark
Automatic
0
Learning monocular 3D reconstruction of articulated categories from motion
Monocular 3D reconstruction of articulated object categories is challenging due to the lack of training data and the inherent …
Filippos Kokkinos
,
Iasonas Kokkinos
PDF
Cite
Project
Supplementary
To The Point: Correspondence-driven monocular 3D category reconstruction
We present To The Point (TTP), a method for reconstructing 3D objects from a single image using 2D to 3D correspondences learned from …
Filippos Kokkinos
,
Iasonas Kokkinos
PDF
Cite
Pixel Adaptive Filtering Units
State-of-the-art methods for computer vision rely heavily on the translation equivariance and spatial sharing properties of …
Filippos Kokkinos
,
Ioannis Marras
,
Matteo Maggioni
,
Gregory Slabaugh
,
Stefanos Zafeiriou
PDF
Cite
Cite
×