I am a Postdoc at the University of British Columbia in the group of Helge Rhodin. Before I was working as a PhD student at the Leibniz University of Hannover from 2015 to 2020. My main research interests are human motion capture and 3D reconstruction. A special focus lies on the application of machine learning techniques such as deep learning, dimensionality reduction and compressed sensing. My current research analyses weakly supervised training of deep neural networks for human pose reconstruction.

Before, I studied Mechatronics at the Leibniz Universität Hannover. During the bachelor studies I focused on robotics and received my B. Sc. in 2012 with a thesis on path planning of autonomous mobile robots. My master thesis Gait Analysis in Monocular Image Sequences using a Morphable Shape Motion Model dealt with 3D reconstruction and animation of human motions.

In 2018 I founded the AI consulting company HEUWA together with a colleague from TNT.

News

  • July, 2021. This summer term 2 I will be teaching DATA 311 at UBC. All information can be found in Canvas.
  • February, 2021. Our paper CanonPose: Self-supervised Monocular 3D Human Pose Estimation in the Wild got accepted to CVPR 2021. The code will be available soon.
  • January, 2021. After several months of waiting for the visa I finally made it to Vancouver for my Postdoc position at the UBC.
  • December, 2020. I received the KI Talent (AI Talent) award for my dissertation which is endowed with a price money of 4000€.
  • July, 2020. Our paper Weakly-supervised Learning of Human Dynamics got accepted to ECCV 2020. The Human Dynamics Dataset will be available soon.
  • April, 2020. I had a successful PhD defense.
  • March, 2020. As soon as Corona allows it I will start as PostDoc at UBC Vancouver in the group of Helge Rhodin.

Publications

Check Google Scholar for a complete list.

2021

*NEW* CanonPose: Self-supervised Monocular 3D Human Pose Estimation in the Wild
Bastian Wandt, Marco Rudolph, Helge Rhodin, Bodo Rosenhahn
CVPR 2021
[pdf]

AudioViewer: Learning to Visualize Sound 
Yuchi Zhang, Willis Peng, Bastian Wandt, Helge Rhodin,
arxiv preprint
[pdf]

Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows
Marco Rudolph, Bastian Wandt, Bodo Rosenhahn
WACV 2021
[pdf]

2020

Weakly-supervised Learning of Human Dynamics
Petrissa Zell, Bodo Rosenhahn, Bastian Wandt
ECCV 2020
[pdf]

2019

Structuring Autoencoders
Marco Rudolph, Bastian Wandt, Bodo Rosenhahn
ICCV 2019 Workshops
 [pdf]

RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation
Bastian Wandt and Bodo Rosenhahn
CVPR 2019
 [pdf, code]

2018

Region-based Cycle-Consistent Data Augmentation for Object Detection
Florian Kluger, Christoph Reinders, Kevin Raetz, Philipp Schelske, Bastian Wandt, Hanno Ackermann, Bodo Rosenhahn
BigData 2018 Road Damage Detection Challenge (Special Award)
 [pdf]

A Kinematic Chain Space for Monocular Motion Capture
Bastian Wandt, Hanno Ackermann, Bodo Rosenhahn
ECCV 2018 Workshops
 [pdf]

Extending HEVC with a Texture Synthesis Framework using Detail-aware Image Decomposition
Bastian Wandt, Thorsten Laude, Bodo Rosenhahn, Jörn Ostermann
PCS 2018
 [pdf]

Detail-aware Image Decomposition for an HEVC-based Texture Synthesis Framework
Bastian Wandt, Thorsten Laude, Bodo Rosenhahn, Jörn Ostermann
DCC 2018
 

Physics-based Models for Human Gait Analysis
Petrissa Zell, Bastian Wandt, Bodo Rosenhahn
Handbook of Human Motion, Springer International Publishing, 2018
 [pdf]

2017

Extending HEVC Using Texture Synthesis
Bastian Wandt, Thorsten Laude, Yiqun Liu, Bodo Rosenhahn, Jörn Ostermann
VCIP 2017
 [pdf]

Optical Flow-based 3D Human Motion Estimation from Monocular Video
Thiemo Alldieck, Marc Kassubeck, Bastian Wandt, Bodo Rosenhahn, Marcus Magnor
GCPR 2017
 [pdf]

Joint 3D Human Motion Capture and Physical Analysis from Monocular Videos
Petrissa Zell, Bastian Wandt, Bodo Rosenhahn
CVPR 2017 Workshops
 [pdf]

2016

3D Reconstruction of Human Motion from Monocular Image Sequences
Bastian Wandt, Hanno Ackermann, Bodo Rosenhahn
TPAMI 2016
 [pdf]

Teaching

2017-2020

Machine Learning (at TNT, Hannover)
Bodo Rosenhahn and Bastian Wandt

2015-2017

Tracking and Matching in Image Sequences (at TNT, Hannover)
Bodo Rosenhahn and Bastian Wandt

Master and Bachelor theses

  • Klassifikation menschlicher Bewegungen in Unterräumen (2017)
  • Modellierung eines Posenraums menschlicher Bewegungen mit Hilfe neuronaler Netze (2017)
  • Representation of Human Motion using Neural Networks (2018)
  • Codierung menschlicher Oberflächenmodelle mittels Neuronaler Netze (2018)
  • Zeitkonsistente Schätzung Menschlicher Posen mittels Neuronaler Netze (2018)
  • Recurrent Neural Networks for Monocular Human Motion Capture (2019)
  • Realtime 3D Human Pose Estimation (2019)
  • Texturesynthesis using Generative Adversarial Networks (2019)
  • Dimensionsreduktionsmethoden zur Kodierung menschlicher Posen (2019)
  • Tiefenschätzung zur 3D Rekonstruktion menschlicher Posen (2019)
  • Roboterkinematikbasierte Registrierung eines Augmented Reality Systems (2019)