Christian Richardt is a Reader (=Associate Professor) and EPSRC-UKRI Innovation Fellow in the Visual Computing Group, the CAMERA Centre and REVEAL at the University of Bath. His research interests cover the fields of image processing, computer graphics and computer vision, and his research combines insights from vision, graphics and perception to reconstruct visual information from images and videos, to create high-quality visual experiences with a focus on 6-degree-of-freedom VR video.

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.

 

---

News

November 2020

We will be presenting our work BlockGAN at NeurIPS 2020.

I co-chaired the ISMAR 2020 Doctoral Consortium, virtually in Brazil.

The European Conference on Visual Media Production (CVMP) on 7–8 December will be free to attend this year. Register here.

September 2020

We will be presenting our work OmniPhotos: Casual 360° VR Photography at SIGGRAPH Asia 2020.

We will be presenting two papers at ISMAR 2020 in November:

• Photorealistic Audio-driven Video Portraits (TVCG journal paper)
• Transitioning360: Content-aware NFoV Virtual Camera Paths for 360° Video Playback

August 2020

We presented two papers at ECCV 2020:

• MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images (oral)
• Combining Task Predictors via Enhancing Joint Predictability

I am co-editing a Research Topic (special issue) on Capturing and Sharing the Real World in Virtual and Augmented Reality in Frontiers in Virtual Reality | Technologies for VR (with Jonathan Ventura and Stefanie Zollmann). Abstracts due 27 October 2020, manuscripts due 3 February 2021.

July 2020

Five papers accepted: two papers at ECCV (one oral), two papers at ISMAR (one TVCG), and one paper conditionally accepted at SIGGRAPH Asia.

June 2020

I co-organised DynaVis – the second workshop on dynamic scene reconstruction at CVPR 2020. Watch the recording on YouTube.

March 2020

I will be chairing the European Conference on Visual Media Production (CVMP) in December 2020.

Three book chapters are now available:

• Capture, Reconstruction, and Representation of the Visual Real World for Virtual Reality: A state-of-the-art review of the VR Capture Pipeline, including neural scene representations
• Image-Based Scene Representations for Head-Motion Parallax in 360° Panoramas
• Omnidirectional Stereo: A new entry in the Computer Vision Reference Guide

November 2019

We presented our HoloGAN paper at ICCV 2019 in Seoul, South Korea.

Hyeongwoo Kim presented our work on neural style-preserving visual dubbing was presented at SIGGRAPH Asia 2019 in Brisbane.

---

Selected publications