Christoph Lassner

Research Scientist

Facebook Reality Labs

Biography

I am a Machine Learning and Computer Vision researcher making machines understand and generate representations of humans in 2D and 3D. I joined Facebook Reality Labs in March 2019 to make my vision of better and easier interaction between humans and machines become a reality.

Before joining Facebook, I worked at a startup which was acquired by Amazon. I did my PhD at the Bernstein Center for Computational Neuroscience Tübingen and the Max Planck Institute for Intelligent Systems.

Interests

Machine Learning
2D and 3D Human Body Modelling
Human Motion Modelling
Differentiable Rendering

Featured Publications

Tiancheng Zhi, Christoph Lassner, Tony Tung, Carsten Stoll, Srinivasa G. Narasimhan, Minh Vo

August 2020

TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video

We propose a new method to reconstruct a mesh-based avatar from RGB-D video taking albedo and lighting into account.

PDF Video

Zeng Huang, Yuanlu Xu, Christoph Lassner, Hao Li, Tony Tung

June 2020

ARCH: Animatable Reconstruction of Clothed Humans

We propose a novel, end-to-end pipeline to reconstruct detailed animatable avatars from a single picture.

PDF

Nadine Rüegg, Christoph Lassner, Michael J. Black, Konrad Schindler

February 2020

Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations

Extending cycle consistency models to learn mappings between 2D images and parameterized 3D models.

PDF

Recent Publications

Quickly discover relevant content by filtering publications.

TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video

We propose a new method to reconstruct a mesh-based avatar from RGB-D video taking albedo and lighting into account.

Tiancheng Zhi, Christoph Lassner, Tony Tung, Carsten Stoll, Srinivasa G. Narasimhan, Minh Vo

PDF Video

ARCH: Animatable Reconstruction of Clothed Humans

We propose a novel, end-to-end pipeline to reconstruct detailed animatable avatars from a single picture.

Zeng Huang, Yuanlu Xu, Christoph Lassner, Hao Li, Tony Tung

PDF

Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations

Extending cycle consistency models to learn mappings between 2D images and parameterized 3D models.

Nadine Rüegg, Christoph Lassner, Michael J. Black, Konrad Schindler

PDF

Efficient Learning on Point Clouds With Basis Point Sets

We propose a novel representation, Basis Point Sets (BPS), for point clouds that allows us to perform deep learning tasks naturally and efficiently.

Sergey Prokudin, Christoph Lassner, Javier Romero

PDF Code

Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation

We propose a novel end-to-end neural network architecture and training scheme to train 3D body pose and shape estimation from 2D images.

Mohamed Omran, Christoph Lassner, Gerard Pons-Moll, Peter V. Gehler, Bernt Schiele

PDF Code

See all publications