Dominic Ruefenacht

Research Associate
IVMP 

Work Address

MSEB Lvl 6
School of Electrical Engineering & Telecomms.
The University of New South Wales
UNSW Sydney NSW 2052, Australia

Email

d (dot) ruefenacht (at) unsw (dot) edu (dot) au

Personal Webpage

http://www.druefenacht.ch

Short Bio

Dominic Ruefenacht received his B.Sc. and M.Sc. in communication systems with specialization in “Signals, Images and Interfaces” from the École Polytechnique Fédérale de Lausanne (EPFL), Switzerland, in 2009 and 2011. He was an exchange student at the University of Waterloo, Ontario, Canada, and did his Master's thesis at Philips Consumer Lifestyle in Eindhoven, Netherlands, entitled “Stereoscopic High Dynamic Range Video”. He obtained his Ph.D. degree from UNSW Sydney, Australia, in 2017, where he was investigating “Novel Motion Anchoring Strategies for Wavelet-based Highly Scalable Video Compression”.
From 2011 to 2013, he was with the Image and Visual Representation Group (IVRG) at EPFL as a research engineer, where he was working on computational photography problems, with emphasis on near-infrared imaging.
He currently holds a post-doctoral position at UNSW Sydney, working on next-generation video compression systems. His research interests are in computational photography and highly scalable and accessible video compression, with a focus on temporal scalability.
More info in full CV.

Research Pages

Teaser Image 

Hierarchical Motion Field Anchoring for Highly Scalable Video Coding
We propose to use ‘‘physical’’ motion rather than block motion, as commonly used in video coding standards. Together with estimated motion discontinuities, this allows to flip the motion field anchoring to the target frames, which has a number of key benefits over the traditional motion anchoring.

Teaser Image 

Motion-Centric Temporal Frame Interpolation
A novel approach for temporal frame interpolation (TFI) which only uses motion information and estimated motion discontinuities in the frame interpolation process. During the motion mapping process, we obtain high-quality disocclusion masks, which are useful to guide the bidirectional frame interpolation process.

Publications

Theses

PhD Thesis

Teaser Image 

D. Ruefenacht, ‘‘Novel Motion Anchoring Strategies for Wavelet-based Highly Scalable Video Compression,’’ UNSW Sydney, Australia, 2017.
Download

Master Thesis

Teaser Image 

D. Ruefenacht, ‘‘Stereoscopic High Dynamic Range Video,’’ EPFL, Switzerland, 2011.
Download

Journal Articles

2016

Teaser Image 

D. Ruefenacht, R. Mathew, and D. Taubman, ‘‘Occlusion-Aware Temporal Frame Interpolation in a Highly Scalable Video Setting,’’ APSIPA Transactions on Signal and Information Processing (ATSIP), 2016.
Preprint | Project Webpage

TIP BIHA Teaser Image 

D. Ruefenacht, R. Mathew, and D. Taubman, “A Novel Motion Field Anchoring Paradigm for Highly Scalable Wavelet-based Video Coding,” IEEE Transactions on Image Processing (TIP).
Preprint | DOI | Project Webpage

2014

NIR Shadows Teaser Image 

D. Ruefenacht, C. Fredembach, and S. Suesstrunk, “Automatic and Accurate Shadow Detection using Near-Infrared Information,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014.
Preprint | DOI | Project Webpage

Conference and Workshop Papers

2017

Teaser Image 

D. Ruefenacht and D. Taubman, “Leveraging Decoded HEVC Motion for Fast, High Quality Optical Flow Estimation,” IEEE International Workshop on Multimedia Signal Processing (MMSP), Luton, UK, 2017.
Preprint

Teaser Image 

D. Ruefenacht and D. Taubman, “HEVC-EPIC: Edge-preserving Interpolation of Coded HEVC Motion with Applications to Framerate Upsampling,” IEEE International Conference on Multimedia and Expo (ICME), Hong Kong, 2017.
Preprint

2016

Teaser Image 

D. Ruefenacht, R. Mathew, and D. Taubman, “Higher-Order Motion Models for Temporal Frame Interpolation with Applications to Video Coding,” Picture Coding Symposium (PCS), Nuremberg, Germany, 2016.
Preprint | Project Webpage

Teaser Image 

D. Ruefenacht and D. Taubman, “Temporally Consistent High Frame-Rate Upsampling with Motion Sparsification,” IEEE International Workshop on Multimedia Signal Processing (MMSP), Montreal, Canada, 2016.
Preprint | Poster

2015

Teaser Image 

D. Ruefenacht, R. Mathew, and D. Taubman, “Motion Blur Modelling for Hierarchically Anchored Motion with Discontinuities,” IEEE International Workshop on Multimedia Signal Processing (MMSP), Xiamen, China, 2015.
Preprint | Poster | Project Webpage

Teaser Image 

D. Ruefenacht, R. Mathew, and D. Taubman, “Bidirectional, Occlusion-Aware Temporal Frame Interpolation in a Highly Scalable Video Setting,” Picture Coding Symposium (PCS), Cairns, Australia, 2015.
Full text | Presentation Slides | Poster | Project Webpage

Teaser Image 

R. Xu, A. Naman, R. Mathew, D. Ruefenacht, and D. Taubman, “Motion Estimation with Accurate Boundaries,” Picture Coding Symposium (PCS), Cairns, Australia, 2015.

2014

Teaser Image 

Top 10% Award
D. Ruefenacht, R. Mathew, and D. Taubman, “Bidirectional Hierarchical Anchoring of Motion Fields for Scalable Video Coding,” IEEE International Workshop on Multimedia Signal Processing (MMSP), Jakarta, Indonesia, 2014.
Full text | DOI | Presentation Slides | Poster

Teaser Image 

D. Ruefenacht, R. Mathew, and D. Taubman, “Hierarchical Anchoring of Motion Fields for Fully Scalable Video Coding,” IEEE International Conference on Image Processing (ICIP), Paris, France, 2014.
Full text | Poster

Teaser Image 

D. Ruefenacht, M. Brown, J. Beutel, and S. Suesstrunk, “Temporally Consistent Snow Cover Estimation from Noisy , Irregularly Sampled Measurements,” International Conference on Computer Vision Theory and Applications (VISAPP), pp. 275–283, 2014.
Full text | Presentation Slides | Project Webpage

2013

Teaser Image 

D. Ruefenacht, G. Trumpy, R. Gschwind, and S. Suesstrunk, “Automatic Detection of Dust and Scratches in Silver Halide Film using Polarized Dark-Field Illumination,” IEEE International Conference on Image Processing (ICIP), Melbourne, Australia, 2013.
Full text | DOI | Presentation Slides