João Regateiro
YOU?
Author Swipe
View article: Neural Implicit Avatar Conditioned on Human Pose, Identity and Gender
Neural Implicit Avatar Conditioned on Human Pose, Identity and Gender Open
International audience
View article: Implicit Shape Avatar Generalization across Pose and Identity
Implicit Shape Avatar Generalization across Pose and Identity Open
The creation of realistic animated avatars has become a hot-topic in both academia and the creative industry. Recent advancements in deep learning and implicit representations have opened new research avenues, particularly in enhancing ava…
View article: Deformation-Guided Unsupervised Non-Rigid Shape Matching
Deformation-Guided Unsupervised Non-Rigid Shape Matching Open
We present an unsupervised data-driven approach for non-rigid shape matching. Shape matching identifies correspondences between two shapes and is a fundamental step in many computer vision and graphics applications. Our approach is designe…
View article: Deep4D: A Compact Generative Representation for Volumetric Video
Deep4D: A Compact Generative Representation for Volumetric Video Open
This paper introduces Deep4D a compact generative representation of shape and appearance from captured 4D volumetric video sequences of people. 4D volumetric video achieves highly realistic reproduction, replay and free-viewpoint rendering…
View article: 3D Human Shape Style Transfer
3D Human Shape Style Transfer Open
We consider the problem of modifying/replacing the shape style of a real moving character with those of an arbitrary static real source character. Traditional solutions follow a pose transfer strategy, from the moving character to the sour…
View article: Learning to animate volumetric video.
Learning to animate volumetric video. Open
4D human performance capture aims to create volumetric representations of observed human subjects performing arbitrary motions with the ability to replay and render dynamic scenes with the realism of the recorded video. This representation…