Publications | Max Planck Institute for Intelligent Systems

11 results (View BibTeX file of all listed publications)

2016

Skinned multi-person linear model

Black, M.J., Loper, M., Mahmood, N., Pons-Moll, G., Romero, J.

December 2016, Application PCT/EP2016/064610 (misc)

Abstract

The invention comprises a learned model of human body shape and pose dependent shape variation that is more accurate than previous models and is compatible with existing graphics pipelines. Our Skinned Multi-Person Linear model (SMPL) is a skinned vertex based model that accurately represents a wide variety of body shapes in natural human poses. The parameters of the model are learned from data including the rest pose template, blend weights, pose-dependent blend shapes, identity- dependent blend shapes, and a regressor from vertices to joint locations. Unlike previous models, the pose-dependent blend shapes are a linear function of the elements of the pose rotation matrices. This simple formulation enables training the entire model from a relatively large number of aligned 3D meshes of different people in different poses. The invention quantitatively evaluates variants of SMPL using linear or dual- quaternion blend skinning and show that both are more accurate than a Blend SCAPE model trained on the same data. In a further embodiment, the invention realistically models dynamic soft-tissue deformations. Because it is based on blend skinning, SMPL is compatible with existing rendering engines and we make it available for research purposes.

Google Patents [BibTex]

2016

ps Black, M.J., Loper, M., Mahmood, N., Pons-Moll, G., Romero, J. Skinned multi-person linear model December 2016, Application PCT/EP2016/064610 (misc)

Google Patents [BibTex]

Special Issue on Causal Discovery and Inference

Zhang, K., Li, J., Bareinboim, E., Schölkopf, B., Pearl, J.

ACM Transactions on Intelligent Systems and Technology (TIST), 7(2), January 2016, (Guest Editors) (misc)

[BibTex]

ei Zhang, K., Li, J., Bareinboim, E., Schölkopf, B., Pearl, J. Special Issue on Causal Discovery and Inference ACM Transactions on Intelligent Systems and Technology (TIST), 7(2), January 2016, (Guest Editors) (misc)

[BibTex]

Empirical Inference (2010-2015)

Scientific Advisory Board Report, 2016 (misc)

pdf [BibTex]

ei Empirical Inference (2010-2015) Scientific Advisory Board Report, 2016 (misc)

pdf [BibTex]

A note on the expected minimum error probability in equientropic channels

Weichwald, S., Fomina, T., Schölkopf, B., Grosse-Wentrup, M.

2016 (misc)

PDF Arxiv [BibTex]

ei Weichwald, S., Fomina, T., Schölkopf, B., Grosse-Wentrup, M. A note on the expected minimum error probability in equientropic channels 2016 (misc)

PDF Arxiv [BibTex]

Unsupervised Domain Adaptation in the Wild : Dealing with Asymmetric Label Set

Mittal, A., Raj, A., Namboodiri, V. P., Tuytelaars, T.

2016 (misc)

Arxiv [BibTex]

ei Mittal, A., Raj, A., Namboodiri, V. P., Tuytelaars, T. Unsupervised Domain Adaptation in the Wild : Dealing with Asymmetric Label Set 2016 (misc)

Arxiv [BibTex]

Perceiving Systems (2011-2015)

Scientific Advisory Board Report, 2016 (misc)

pdf [BibTex]

ps Perceiving Systems (2011-2015) Scientific Advisory Board Report, 2016 (misc)

pdf [BibTex]

Can Modular Finger Control for In-Hand Object Stabilization be accomplished by Independent Tactile Feedback Control Laws?

Veiga, F., Peters, J.

2016 (misc)

arXiv [BibTex]

ei Veiga, F., Peters, J. Can Modular Finger Control for In-Hand Object Stabilization be accomplished by Independent Tactile Feedback Control Laws? 2016 (misc)

arXiv [BibTex]

Extrapolation and learning equations

Martius, G., Lampert, C. H.

2016, arXiv preprint \url{https://arxiv.org/abs/1610.02995} (misc)

Project Page [BibTex]

al Martius, G., Lampert, C. H. Extrapolation and learning equations 2016, arXiv preprint \url{https://arxiv.org/abs/1610.02995} (misc)

Project Page [BibTex]

2014

Local Gaussian Regression

Meier, F., Hennig, P., Schaal, S.

arXiv preprint, March 2014, clmc (misc)

Abstract

Abstract: Locally weighted regression was created as a nonparametric learning method that is computationally efficient, can learn from very large amounts of data and add data incrementally. An interesting feature of locally weighted regression is that it can work with ...

am pn

Web link (url) [BibTex]