Tomas Simon

Robotics Institute
Carnegie Mellon University
Office: Smith Hall 201

I am a PhD student at Carnegie Mellon University, advised by Yaser Sheikh at the Robotics Institute and Iain Matthews from Disney Research.

My research is in computer vision and graphics, and I am interested in the spatiotemporal modeling of 3D motion, particularly for natural and dynamic objects such as faces and bodies.

My current research topics include spatio-temporal modeling and editing, non-rigid structure from motion, and statistical learning for time-series data.



Research

Hand Keypoint Detection in Single Images using Multiview Bootstrapping

Tomas Simon, Hanbyul Joo, Iain Matthews, Yaser Sheikh
Computer Vision and Pattern Recognition (CVPR), 2017

arXiv | video | project

Kronecker-Markov Prior for Dynamic 3D Reconstruction

Tomas Simon, Jack Valmadre, Iain Matthews, Yaser Sheikh
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016

pdf | video (slides)

(MP4, 25 MB)

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields

Zhe Cao, Tomas Simon, Shih­-En Wei, Yaser Sheikh
arXiv:1611.08050, November 2016

arXiv | video | code

Realtime Multiperson Pose Estimation

Zhe Cao, Shih­-En Wei, Tomas Simon, Yaser Sheikh
Best Demo Award, European Conference on Computer Vision (ECCV), 2016

MS COCO Keypoint Challenge | slides

Panoptic Studio: A Massively Multiview System for Social Interaction Capture

Hanbyul Joo, Tomas Simon, Xulong Li, Hao Liu, Lei Tan, Lin Gui, Sean Banerjee, Timothy Godisart, Bart Nabbe, Iain Matthews, Takeo Kanade, Shohei Nobuhara, Yaser Sheikh
arXiv:1612.03153, December 2016

arXiv | project | video | code

Photogeometric Scene Flow for High-Detail Dynamic 3D Reconstruction

Paulo Gotardo, Tomas Simon, Yaser Sheikh, Iain Matthews
International Conference on Computer Vision (ICCV), 2015

pdf | project | video

Separable Spatiotemporal Priors for Convex Reconstruction of Time-Varying 3D Point Clouds

Tomas Simon, Jack Valmadre, Iain Matthews, Yaser Sheikh
European Conference on Computer Vision (ECCV), 2014

pdf | project | video spotlight

(MOV, 9 MB)

| BibTeX

3D Object Manipulation in a Single Image using Stock 3D Models

Natasha Kholgade, Tomas Simon, Alexei Efros, Yaser Sheikh
ACM Transactions on Graphics (TOG), July 2014

pdf | project | video

(MOV, 24 MB)

| BibTeX

Bilinear Spatiotemporal Basis Models

Ijaz Akhter, Tomas Simon, Sohaib Khan, Iain Matthews, Yaser Sheikh
ACM Transactions on Graphics (TOG), April 2012

pdf | project | video

(MOV, 94 MB)

| BibTeX

FAST-FACS: A Computer-Assisted System to Increase Speed and Reliability of Manual FACS Coding

Fernando De la Torre, Tomas Simon, Zara Ambadar, Jeffrey Cohn
Affective Computing and Intelligent Interaction (ACII), 2011

pdf | BibTeX

Action Unit Detection with Segment-based SVMs

Tomas Simon, Minh Nguyen, Fernando De la Torre, Jeffrey Cohn
IEEE Computer Vision and Pattern Recognition (CVPR), 2010

pdf | BibTeX

Detecting Depression from Facial Actions and Vocal Prosody

Jeffrey Cohn, Tomas Simon, Iain Matthews, Ying Yang, Minh Nguyen, Margara Tejera, Feng Zhou, Fernando De la Torre
Affective Computing and Intelligent Interaction (ACII), 2009

pdf | BibTeX