Tomas Jakab

7

Papers

62

Total Citations

Papers (7)

Learning the 3D Fauna of the Web

VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control

MagicPony: Learning Articulated 3D Animals in the Wild

Self-Supervised Learning of Interpretable Keypoints From Unlabelled Videos

DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction

Unsupervised Learning of Object Landmarks through Conditional Image Generation