Suryansh
 
Computer Vision Lab, ETH Zurich
Résumé (on request)
sukumar at vision dot ee.ethz.ch
     

I am a computer science researcher primarily focused on 3D computer vision. I work at the Computer Vision Lab and Visual Intelligence and System Lab in the Department of Information Technology and Electrical Engineering (DITET) at ETH Zürich. As a researcher, I am fascinated by how mathematical construction can precisely represent the perceptual concepts of images, such as 3D scene geometry, motions, lights, and color. I aim to use these mathematical concepts to enable machines for a broader adoption using visual data. Presently, I supervise and work on projects that ETH Zürich Foundation support. Before ETH Zürich, I was a HDR merit scholarship Ph.D. student at Australian National University (ANU), funded by the Australian Research Council. I received a Ph.D. in Engineering and Computer Science on the thesis titled Non-Rigid Structure from Motion, which was nominated for J. G. Crawford Prize at ANU for Best Ph.D. Thesis 2019.

Research Interests

Geometric Computer Vision, Mathematical Optimization, Abstract Algebra, Geometric AI and Robotics. From time to time, I also investigate topics such as graph theory, topological manifolds and compressed sensing.

Recent News

[02-2023]   Two research papers accepted for publication at CVPR 2023.
[01-2023]   Three research papers accepted for publication, one at each venue: ICLR, ICRA, RAL 2023.
[07-2022]   Two research papers accepted for publication at ECCV 2022.
[05-2022]   Invited talk at Google Developer Student Club, Zurich.
[03-2022]   Three research papers accepted for publication at CVPR 2022.
[02-2022]   Invited talk at Warren Grundfest Lecture series co-organized by UCLA and Caltech.
[01-2022]   One research paper accepted for publication at RAL, ICRA 2022.

Recent Awards and Achievements

  • Successfully concluded Google Focused Research Project in Nov'22. Co-authored with Prof. Luc Van Gool and Prof. Vittorio Ferrari.
  • Nominated for J. G. Crawford Prize at ANU for Best Interdisciplinary Ph.D. Thesis 2019.
  • Australian National University Vice-Chancellor Grant Award.
  • Best Algorithm Award in CVPR NRSFM Challenge 2017 by Disney Research.
  • ANU-HDR Merit Scholarship Student Award, funded in part by The Australian Research Council.

Current Students (Masters and Doctorate)

  • Wenkel Jan (M.S) ETH Zurich, (Feb. 23-).
    [Topic]: Continous Curvature Analysis.
  • Marcus Leong (M.S) ETH Zurich, (Feb. 23-).
    [Topic]: Active SLAM.
  • Ozgur Fikrican (M.S) ETH Zurich, (Oct. 22-).
    [Topic]: Robotic Manipulation.
  • Erik Sandström (Ph.D.), ETH Zurich, (Nov. 19-).
    [Topic]: Online dense 3D reconstruction.
  • Ce Liu (Ph.D.) ETH Zurich, (Sept. 22-).
    [Topic]: Learning based 3D reconstruction.

External Students or Informal Collaboration

  • Yasaman Haghighi (M.S) EPFL (Sept. 22-).
    [Topic]: Visual SLAM.
  • Zhou Haonan (M.S) Imperial College London (Dec. 22-).
    [Topic]: Robot Vision and Control.
  • Yue Shi [Advise] Ph.D., Shanghai Jiao Tong University (Jan. 23-).
    [Topic]: Neural Radiance Fields.
  • Nishant Jain [Advise] Google Research (Oct. 22-).
    [Topic]: Novel View Synthesis.
  • Benedek Forrai [Advise] Ph.D., ETH Zurich (Jan. 23-).
    [Topic]: Robotic Manipulation.
  • Jelena Trisovic [Advise] Ph.D., ETH Zurich (Mar. 22-).
    [Topic]: Visual Perception and Control.
  • René Zurbrügg [Advise] Ph.D., ETH Zurich (July. 22-).
    [Topic]: Robotic Manipulation.

Work Contract at ETH Zurich for the year 2023

Selected Recent Publications

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take
Authors: Ce Liu, Suryansh Kumar, Shuhang Gu, Radu Timofte, Luc Van Gool.
Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2023, Vancouver, Canada.

  Project Website (Soon)     Topic: 3D Computer Vision, Deep Learning.
Enhanced Stable View-Synthesis
Authors: Nishant Jain*, Suryansh Kumar*, Luc Van Gool.
Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2023, Vancouver, Canada.

  Project Website (Soon)     Topic: 3D Computer Vision, Deep Learning, Neural Rendering.
VA-DepthNet: A Variational Approach to Single Image Depth Prediction
Authors: Ce Liu, Suryansh Kumar, Shuhang Gu, Radu Timofte, Luc Van Gool. (Spotlight Oral Presentation)
International Conference on Learning Representations (ICLR), 2023, Kigali, Rwanda.

  Project Website     Topic: 3D Computer Vision, Deep Learning.
Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields
Authors: Soomin Lee, Le Chen, Jiahao Wang, Alexander Liniger, Suryansh Kumar, Fisher Yu.
International Conference on Robotics and Automation (ICRA), IEEE, 2023, London, UK. (Oral Presentation)

  Project Website     Topic: 3D Computer Vision, Robotics, Information Theory.
Organic Priors in Non-Rigid Structure from Motion
Authors: Suryansh Kumar, Luc Van Gool. (Oral Presentation, Top 2.7% of the papers)
European Conference on Computer Vision (ECCV), 2022, Tel-Aviv, Israel.

  Project Website     Topic: 3D Computer Vision, Algebra, Geometry, Compressed Sensing.
Uncertainty Aware Deep Multi-View Photometric Stereo
Authors: Berk Kaya, Suryansh Kumar, Carlos Oliveira, Vittorio Ferrari, Luc Van Gool.
Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2022, New Orleans, USA.

  Project Website     Topic: 3D Computer Vision, Machine Learning
Generative Flows with Invertible Attentions
Authors: Rhea Sukthanker, Zhiwu Huang, Suryansh Kumar, Radu Timofte, Luc Van Gool.
Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2022, New Orleans, USA.

  Project Website     Topic: Generative Models, Image Processing
Robustifying the Multi-Scale Representation of Neural Radiance Fields
Authors: Nishant Jain, Suryansh Kumar, Luc Van Gool. (Oral Presentation)
British Machine Vision Conference (BMVC), 2022, London, UK.

  Project Website     Topic: 3D Computer Vision, View Synthesis, Neural Rendering.