75 citations · 376 across the 56 of their papers we have counts for
12 papers · 1 filter
Learning Complex 3D Human Self-Contact
Mihai Fieraru, Mihai Zanfir, Elisabeta Oneata +3
Monocular estimation of three dimensional human self-contact is fundamental for detailed scene analysis including body language understanding and behaviour modeling. Existing 3d re…
Embodied Visual Active Learning for Semantic Segmentation
David Nilsson, Aleksis Pirinen, Erik Gärtner +1
We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting vi…
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration
Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt +1
We address the problem of fitting 3D human models to 3D scans of dressed humans. Classical methods optimize both the data-to-model correspondences and the human model parameters (p…
Neural Descent for Visual 3D Human Pose and Shape
Andrei Zanfir, Eduard Gabriel Bazavan, Mihai Zanfir +3
We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistic…
Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction
Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt +1
Implicit functions represented as deep learning approximations are powerful for reconstructing 3D surfaces. However, they can only produce static surfaces that are not controllable…
Post-hoc Calibration of Neural Networks by g-Layers
Amir Rahimi, Thomas Mensink, Kartik Gupta +3
Calibration of neural networks is a critical aspect to consider when incorporating machine learning models in real-world decision-making systems where the confidence of decisions a…