University of Bath

Intel Visual Computing Institute

Max-Planck-Institut für Informatik

Inria logo

University of Cambridge logo

Portrait photo of Christian RichardtChristian Richardt is a Lecturer (=Assistant Professor) in the Visual Computing Group, the CAMERA Centre and the MARVEL Lab at the University of Bath. His research interests cover the fields of image processing, computer graphics and computer vision, with a focus on video processing for 360 degree videos, light fields, and for user-centric applications.

Christian is also interested in stereoscopic vision and graphics, computational photography and non-photorealistic rendering (NPR). In his work, he also often builds on insights from human visual perception and use techniques from multi-view geometry. He enjoys teaching, mentoring and supervising student projects – many of which have received project prizes at Cambridge.

Christian was previously a postdoctoral researcher working on user-centric video processing and motion capture with Christian Theobalt at the Intel Visual Computing Institute at Saarland University and also in the Graphics, Vision and Video group at Max-Planck-Institut für Informatik in Saarbrücken, Germany. Previously, he was a postdoc in the REVES team at Inria Sophia Antipolis, France, working with George Drettakis and Adrien Bousseau, and he interned with Alexander Sorkine-Hornung at Disney Research Zurich where he worked on Megastereo panoramas.

Christian graduated with a PhD and BA from the University of Cambridge in 2012 and 2007, respectively. His PhD in the Computer Laboratory’s Rainbow Group was supervised by Neil Dodgson. His doctoral research investigated the full life cycle of videos with depth (RGBZ videos): from their acquisition, via filtering and processing, to the evaluation of stereoscopic display.


NEW! Postdoc and software engineer opportunities

I am looking for a postdoctoral researcher and a research software engineer (ideally 32 months starting in October 2018) to work on dynamic scene reconstruction from multi-view camera rigs for immersive 6-degree-of-freedom VR Video. If you’re interested, please contact me via email.

I am looking for students!

Are you interested in visual computing, computer graphics, computational photography or video processing? I am looking for motivated students at all levels, from Bachelor’s, Master’s to PhD level. Please contact me if you are interested.


August 2018
At SIGGRAPH 2018 in Vancouver, we will present our work Deep Video Portraits, Parallax360 and MegaParallax (poster).

June 2018
I have been awarded a UKRI Innovation Fellowship to work on 6-DoF VR Video.

We presented two papers at CVPR 2018: Live Intrinsic Material Estimation (spotlight) and InverseFaceNet.

May 2018
We will present our Deep Video Portraits at SIGGRAPH 2018 in Vancouver!

April 2018
We will present our IEEE TVCG paper “Parallax360” in a special invited TVCG session on VR/AR at SIGGRAPH 2018.

March 2018
I was co-presenting a full-day tutorial on Cutting-edge VR/AR Display Technologies at IEEE VR 2018 in Reutlingen, Germany.
Also at IEEE VR, we presented our IEEE TVCG paper “Parallax360: Stereoscopic 360° Scene Representation for Head-Motion Parallax”.

February 2018
Two papers accepted to CVPR 2018: Live Intrinsic Material Estimation (spotlight) and InverseFaceNet.

December 2017
Our paper “Parallax360: Stereoscopic 360° Scene Representation for Head-Motion Parallax” was accepted as an IEEE TVCG journal paper at IEEE VR 2018 in Reutlingen, Germany.

We presented two short papers at CVMP 2017: on undoing Instagram filters and dynamic mixed-reality compositing.

November 2017
Our egocentric motion-capture approach “EgoCap” won the Best Poster Award at Motion in Games 2017.

October 2017
Abhi and Gereon presented our work on live user-guided intrinsic video decomposition at ISMAR 2017.

August 2017
I co-organised a course at SIGGRAPH 2017 on Video for Virtual Reality, which covers the technical foundations, current systems in practice, and the potential for future systems of VR video.

July 2017
Our work on live user-guided intrinsic video decomposition has been accepted at ISMAR 2017 and in IEEE TVCG, and our work on combining predictors at test time has been accepted at ICCV 2017.

Selected publications

LIME: Live Intrinsic Material Estimation
Abhimitra Meka, Maxim Maximov, Michael Zollhöfer, Avishek Chatterjee, Hans-Peter Seidel, Christian Richardt and Christian Theobalt
Conference on Computer Vision and Pattern Recognition (CVPR) 2018 (spotlight presentation)

Parallax360: Stereoscopic 360° Scene Representation for Head-Motion Parallax
Bicheng Luo, Feng Xu, Christian Richardt and Jun-Hai Yong
IEEE Transactions on Visualization and Computer Graphics (IEEE VR 2018)

Video for Virtual Reality
Christian Richardt, James Tompkin, Jordan Halsey, Aaron Hertzmann, Jonathan Starck and Oliver Wang
Course at SIGGRAPH 2017 (Thursday, 3 August, 9:00–12:15, Room 403AB)

EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras
Helge Rhodin, Christian Richardt, Dan CasasEldar Insafutdinov, Mohammad Shafiei, Hans-Peter SeidelBernt Schiele and Christian Theobalt
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2016)

Dense Wide-Baseline Scene Flow From Two Handheld Video Cameras
Christian Richardt, Hyeongwoo Kim, Levi Valgaerts and Christian Theobalt
International Conference on 3D Vision 2016 (oral presentation, 9.8% acceptance rate)

Video Depth-From-Defocus
Hyeongwoo Kim, Christian Richardt and Christian Theobalt
International Conference on 3D Vision 2016

General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues
Helge Rhodin, Nadia Robertini, Dan Casas, Christian Richardt, Hans-Peter Seidel and Christian Theobalt
European Conference on Computer Vision 2016 (spotlight presentation, 2.9% acceptance rate)

Live Intrinsic Video
Abhimitra Meka, Michael Zollhöfer, Christian Richardt and Christian Theobalt
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2016)

Megastereo: Constructing High-Resolution Stereo Panoramas
Christian Richardt, Yael Pritch, Henning Zimmer and Alexander Sorkine-Hornung
Proceedings of CVPR 2013 (oral presentation, 3.3% acceptance rate)

Real-time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid
Christian Richardt, Douglas Orr, Ian DaviesAntonio Criminisi and Neil A. Dodgson
European Conference on Computer Vision 2010 (Poster + Demo)