Songyou Peng (彭崧猷)

I am an incoming PhD student at ETH Zurich and Max Planck Institute for Intelligent Systems as part of Max Planck ETH Center for Learning Systems.

Previously, I was a research engineer at Advanced Digital Sciences Center (ADSC), a research center of University of Illinois Urbana-Champaign (UIUC) based in Singapore. I was also working at Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore.

I completed a Erasmus Mundus Masters in Computer Vision and Robotics (VIBOT) with distinction. During the master, I was fortunate to be supervised by Daniel Cremers at Technical University of Munich (TUM) for my thesis and work with Peter Sturm at INRIA Grenoble for two summers. Before this, I obtained a Bachelors in Automation at Xi'an Jiaotong University (XJTU).

Email  /  CV  /  GitHub  /  Google Scholar  /  LinkedIn

  • 07/2019: One paper is accepted to ICCV 2019 as oral presentation! See the highlight.
  • 06/2019: One paper is accepted to TPAMI 2019!
  • 07/2018: One paper is accepted to ACM MM as Technical Demo.
  • 05/2018: In OMG-Emotion Challenge 2018, our ADSC team ranked 1st for vision-only arousal/valence prediction and 2nd for overall valence prediction!
  • 10/2017: I presented my work on ICCV 2017 Color and Photometry in Computer Vision Workshop.

I am interested in computer vision, 3D vision and deep learning.

Calibration Wizard: A Guidance System for Camera Calibration Based on Modelling Geometric and Corner Uncertainty
Songyou Peng and Peter Sturm
International Conference on Computer Vision (ICCV), 2019 (Oral)

A novel system that interactively guides a user towards taking optimal calibration images.

Photometric Depth Super-Resolution
Bjoern Haefner*, Songyou Peng*, Alok Verma*, Yvain Queau, Daniel Cremers
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019. In press.
(* equal contribution)
paper / project page

Photometric techniques to recover high-resolution depth maps with fine geometric details.

PersEmoN: A Deep Network for Joint Analysis of Apparent Personality, Emotion and Their Relationship
Le Zhang, Songyou Peng, Stefan Winkler
In Submission

Give Me One Portrait Image, I Will Tell You Your Emotion and Personality
Songyou Peng, Le Zhang, Stefan Winkler, Marianne Winslett
ACM International Conference on Multimedia (ACM MM), 2018
paper / bibtex / slides

Technical Demo. A deep Siamese-like network is introduced to predict one's Big-Five personality and arousal-valence emotion from one portrait photo.

Depth Super-Resolution Meets Uncalibrated Photometric Stereo
Songyou Peng, Bjoern Haefner, Yvain Queau, Daniel Cremers
International Conference on Computer Vision (ICCV) Workshops, 2017
paper / bibtex / slides / code & data

A novel depth super-resolution approach for RGB-D sensors is presented.

High Quality Shape from a RGB-D Camera using Photometric Stereo
Songyou Peng
M.Sc. Thesis, Techinical University of Munich
Supervisor: Yvain Queau and Daniel Cremers
thesis / bibtex / poster

Selected Projects

A Deep Network for Arousal-Valence Emotion Prediction with Acoustic-Visual Cues
Songyou Peng, Le Zhang, Yutong Ban, Meng Fang, Stefan Winkler
IJCNN One-Minute Gradual (OMG) Emotion Behavior Challenge, 2018
leaderboard / arxiv / code

1st for vision-only arousal/valence prediction and 2nd for overall valence prediction.

A Hybrid SLAM and Object Recognition System for Pepper Robot
Songyou Peng*, Kaisar Kushibar*, Paola Ardon*
VIBOT Robotics Project, 2016
arxiv / video / code

We apply visual SLAM on the Pepper robot along with object recognition.

template from this awesome website
Last updated: July 2019