Songyou Peng (彭崧猷)

I am a Research Scientist at Google DeepMind in San Francisco, USA.

I received my PhD from ETH Zurich and Max Planck Institute for Intelligent Systems under the supervision of Marc Pollefeys and Andreas Geiger. After the PhD, I worked as a Senior Researcher/Postdoc at ETH Zurich for 6 months.

I was a research intern at Google Research with Tom Funkhouser, Meta Reality Labs Research with Michael Zollhoefer, Technical University of Munich with Daniel Cremers, and INRIA with Peter Sturm. I completed an Erasmus Mundus Masters in Computer Vision and Robotics (VIBOT) with distinction, and a Bachelors in Automation at Xi'an Jiaotong University.

Email  |  CV  |  GitHub  |  Google Scholar  |  LinkedIn  |  Twitter

• 10/2024 I am honored to receive the ECVA PhD Award at ECCV 2024!
• 09/2024 WildGaussians and RENOVATE are accepted to NeurIPS 2024!
• 07/2024 Segment3D is accepted to ECCV 2024! Also, I will be co-organizing two workshops: Foundation Models Creators Meet Users (FOCUS) and Open-Vocabulary 3D Scene Understanding (OpenSUN3D).
• 05/2024 Career Update: I start working as a research scientist at Google DeepMind!
---- show more ----
03/2024 Our papers NeRF On-the-go and 3D Neural Edge Reconstruction are accepted to CVPR 2024! Congrats on the successful master theses of my amazing students at ETH Zurich, Lei Li and Weining Ren!
03/2024 NICER-SLAM received the Best Paper Honorable Mention Award at 3DV 2024!
03/2024 Invited to give a talk on 2D Magic in a 3D World at Imperial College London and the University of Hong Kong.
11/2023 I successfully defended my PhD! [Thesis][Defense Slides]
10/2023 Our papers NICER-SLAM and FastHuman are accepted to 3DV 2024.
07/2023 I served as an Area Chair at 3DV 2024.
07/2023 I received the Best Presentation Award at ICVSS 2023!
07/2023 Our paper DiffDreamer is accepted to ICCV 2023! Congrats Shengqu on a successful master thesis!
07/2023 Invited to give a 90-min lecture at SGP 2023 graduate school in neural explicit-implicit representations!
03/2023 I Co-organize OpenSUN3D: 1st Workshop on Open-Vocabulary 3D Scene Understanding in ICCV 2023.
03/2023 Our paper OpenScene from my internship at Google Research is accepted to CVPR 2023!
10/2022 Invited to give a talk on large-scale scene reconstruction with NeRF at Stanford University (Slides).
09/2022 Our paper MonoSDF is accepted to NeurIPS 2022.
09/2022 Invited to give a talk on neural rendering at Adobe Research (Slides).
06/2022 This summer I will be a research intern at Google Research.
06/2022 1st place winner in partial object recovery and 2nd place overall of SHARP Challenge! Congratulations on my students Lei, Zhizheng, Weining, and Liudi from 3D Vision course project at ETH Zurich!
05/2022 Selected as an outstanding reviewer at CVPR 2022.
03/2022 Our paper NICE-SLAM is accepted to CVPR 2022!
02/2022 Invited to talk about Shape As Points at Talking Papers Podcast. Great chat with Yizhak Ben-Shabat!
12/2021 Gave a talk again this year at GAMES Seminar Series on Shape As Points.
09/2021 Our Shape As Points is accepted to NeurIPS 2021 as oral presentation (top 0.6%)!
08/2021 Join Facebook Reality Labs (FRL) as a research intern this fall.
07/2021 Two papers (UNISURF and KiloNeRF) are accepted to ICCV 2021!
06/2021 Gave a talk at GAMES Seminar Series on Towards Practical Applications of NeRF.
11/2020: A master course project that I advised on got accepted to WACV 2021.
08/2020: Start my 1-year stay at Autonomous Vision Group (AVG) at MPI Tübingen.
07/2020 Our paper Convolutional Occupancy Networks is accepted to ECCV 2020 as spotlight (top 5%)!
09/2019 Start PhD journey at Max Planck ETH Center for Learning Systems!
07/2019 Our paper Calibration Wizard is accepted to ICCV 2019 as oral presentation (top 4.6%) .
06/2019: The extension of my master thesis got accepted to TPAMI 2019!

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

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

This paper a part of my master thesis, and subsumed by our TPAMI paper.

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

• Jan Ackermann (Ongoing): MSc student at ETH Zurich
  
  • Semester thesis: Continual Learning of 3D Gaussian Splatting
  • → Master thesis at Stanford University, advised by Gordon Wetzstein
  
  
• Gonca Yilmaz (2024): MSc student at University of Zurich
  
  • Semester thesis: Open Vocabulary Segmentation from Multi-Modal Inputs (ICCVW'23)
  • Master thesis: OpenDAS: Open-Vocabulary Domain Adaption for Segmentation (ICLR'24 submission)
  • → Software engineer at Google
  
  
• Weining Ren (2023): MSc student at ETH Zurich
  
  • Master thesis: NeRF On-the-go (CVPR'24)
  • → PhD student at The University of Hong Kong (HKU), advised by Kai Han
  
  
• Lei Li (2023): MSc student at ETH Zurich
  
  • Master thesis: 3D Neural Edge Reconstruction (CVPR'24)
  • → Computer vision engineer at ByteDance
  
  
• Mirlan Karimov (2023): MSc student at ETH Zurich
  
  • Master thesis: Interactive Preprocessing via Multi-Modal Prompting for NeRFs
  • → PhD student at Mercedes-Benz AG
  
  
• Shengqu Cai (2022): MSc student at ETH Zurich
  
  • Master thesis: DiffDreamer (ICCV'23)
  • → PhD student at Stanford University, advised by Gordon Wetzstein
  
  
• Zihan Zhu (2021): BSc student at Zhejiang University
  
  • Bachelor internship project: NICE-SLAM (CVPR'22)
  • Semester project: NICER-SLAM (3DV'24, Best Paper Honorable Mention)
  • Master thesis (Ongoing): Leverage geometric constraints for better depth estimation
  • → Direct doctorate student at ETH Zurich, advised by Marc Pollefeys
  
  
• Pfister Severin (2021): MSc student at ETH Zurich
  
  • Master thesis: Online Implicit Reconstruction
  • → Consultant at McKinsey & Company
  
  
• Weirong Chen (2020): MSc student at ETH Zurich
  
  • Semester thesis: Real-time 3D Reconstruction through Neural Implicit Representation
  • → PhD student at TU Munich, advised by Daniel Cremers and Andrea Vedaldi

3D Textured Shape Recovery with Learned Geometric Priors
Lei Li, Zhizheng Liu, Weining Ren, Liudi Yang, F. Wang, Marc Pollefeys, Songyou Peng
Shape Recovery from Partial Textured 3D Scans (SHARP), 2022
leaderboard | arxiv | code

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

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

• Publicity Chair: 3DV'25
  
• Area Chair: 3DV'24
  
• Workshop Organizer: OpenSUN3D at ICCV'23 (1st), CVPR'24 (2nd), and ECCV'24 (3rd), FOCUS at ECCV'24
  
• Conference Reviewer: CVPR, ICCV, ECCV, ICLR, NeurIPS, SIGGRAPH, SIGGRAPH Asia
  
• Journal Reviewer: TPAMI, IJCV, CVIU

template adapted from this awesome website