Suryansh Kumar
Assistant Professor in Visual Computing and Computational MediaQuick Information
Contact
- Email Suryansh Kumar
- LAAH, 202
Affiliations
- Visual Computing and Computational Media (VCCM)
Helpful Links
Biography
Dr. Kumar received his Ph.D. in engineering and computer science from the Australian National University (ANU), Canberra, in December 2019. He completed his M.S. in computer science and engineering from the International Institute of Information Technology, Hyderabad (IIIT-H), in 2013. Before joining Texas A&M University, he completed his professorship and post-doctoral research in the Computer Vision Lab at ETH Zürich under the guidance of Prof. Dr. Luc Van Gool. He also worked as a visiting scientist in the e-Motion Group at INRIA Rhône Alpes Grenoble. He has published over 35 peer-reviewed papers at the top-most venues in computer science. He regularly serves as a reviewer for CVPR, ECCV, ICLR, TPAMI, and ICRA. He received the Best Algorithm Award in CVPR 2017 from Disney Research for his work on non-rigid 3D reconstruction. His Ph.D. thesis received a nomination for the J. G. Crawford Prize at ANU for Best Interdisciplinary Ph.D. Thesis for the year 2019. His research interests include computer vision, generative AI, robotics, machine learning, and mathematical optimization.
Education
Ph.D. in Engineering and Computer Science
Australian National University, Canberra, Australia
Awarded: December 2019.
Thesis Panel: Yuchao Dai, Hongdong Li, Richard Hartley
M.S in Computer Science and Engineering
IIIT-Hyderabad, India
Awarded: July 2013.
Thesis Advisor: K Madhava Krishna
Scholarly Interests
- Visual AI, Spatial AI
- Computer Vision
- Generative Modeling
- Robotics and Automation
- Motion Capture Systems
- Other topics of general interests includes graph theory, topological manifolds, compressed sensing, and mathematical optimization.
Courses
Generative AI for Art and Content Creators
Foundations Visual Computing
Research + News
Staff Publications
-
2024 "Evidential Transformers for Improved Image Retrieval", European Conference on Computer Vision (ECCV) 2024, Milano. Italy View
-
2024 "Stereo Risk: A Continuous Modeling Approach to Stereo Matching", International Conference on Machine Learning (ICML) 2024, Vienna, Austria (Oral Paper) View
-
2024 "ICGNet: A Unified Approach for Instance-Centric Grasping", IEEE International Conference on Robotics and Automation (ICRA) 2024, Yokohama, Japan View
-
2024 "Learning Robust Multi-Scale Representation for Neural Radiance Fields from Unposed Images", International Journal of Computer Vision (IJCV), Impact Factor: 19.5 View
-
2023 "Single Image Depth Prediction Made Better: A Multivariate Gaussian Take", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) View
-
2023 " Enhanced Stable View-Synthesis", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) View
-
2023 "VA-DepthNet: A Variational Approach to Single Image Depth Prediction", International Conference on Learning Representations (ICLR), Kigali Rwanda, (Spotlight Oral) View
-
2023 "How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers", Robotics Science and Systems (RSS) View
-
2023 "Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields", IEEE International Conference on Robotics and Automation (ICRA), London, UK (Oral) View
-
2023 "Uncertainty-Driven Dense Two-View Structure from Motion", IEEE International Conference on Intelligent Robots and Systems (IROS), Detroit, USA (Oral) View
-
2023 "Multi-View Photometric Stereo Revisited", IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) View