Evidential Transformers for Improved Image Retrieval
Third Workshop on Uncertainty Quantification for Computer Vision
European Conference on Computer Vision (ECCV), 2024, Milano, Italy
Danilo Dordevic, Suryansh Kumar
Conference Proceedings
Stereo Risk: A Continuous Modeling Approach to Stereo Matching
International Conference on Machine Learning (ICML), 2024, Vienna, Austria. [ Oral, Top 1.5% ]
Ce Liu*, Suryansh Kumar*, Shuhang Gu, Radu Timofte, Yao Yao, Luc Van Gool, (* Equal Contribution)
ICGNet: A Unified Approach for Instance-Centric Grasping
IEEE International Conference on Robotics and Automation (ICRA), 2024, Yokohama, Japan.
René Zurbrügg, Yifan Liu, Francis Engelmann, Suryansh Kumar, Marco Hutter, and others
How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers
Robotics Science and Systems (RSS), RSS Foundation, 2023, Daegu, South Korea.
Junting Chen, Guohao Li, Suryansh Kumar*, and others
Single Image Depth Prediction Made Better: A Multivariate Gaussian Take
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Vancouver, Canada.
Ce Liu, Suryansh Kumar*, Shuhang Gu, Radu Timofte, Luc Van Gool
Enhanced Stable View-Synthesis
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Vancouver, Canada.
Nishant Jain*, Suryansh Kumar*, Luc Van Gool, (* Equal Contribution)
Quantum Annealing for Single Image Super-Resolution
8th New Trends in Image Restoration and Enhancement Workshop and Challenges (NTIRE)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Vancouver, Canada.[ Oral ]
Han Yao Choong, Suryansh Kumar*, Luc Van Gool
VA-DepthNet: A Variational Approach to Single Image Depth Prediction
International Conference on Learning Representations (ICLR), 2023, Kigali, Rwanda.[ Spotlight Oral ]
Ce Liu, Suryansh Kumar*, Shuhang Gu, Radu Timofte, Luc Van Gool
Uncertainty-Driven Dense Two-View Structure from Motion
IEEE International Conference on Intelligent Robots and Systems (IROS), 2023, Detroit, USA.[ Oral ]
Weirong Chen, Suryansh Kumar*, and others, (Oral Presentation)
Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields
IEEE International Conference on Robotics and Automation (ICRA), 2023, London, UK. [ Oral ]
Soomin Lee, Le Chen, Jiahao Wang, Alex Liniger, Suryansh Kumar*, and others
Multi-View Photometric Stereo Revisited
IEEE Winter Conference on Computer Vision (WACV), 2023, Hawaii, USA.
Berk Kaya, Suryansh Kumar, Carlos Oliveira, Vittorio Ferrari, Luc Van Gool
Robustifying the Multi-Scale Representation of Neural Radiance Fields
British Machine Vision Conference (BMVC), 2022, London, UK.[ Oral ]
Nishant Jain, Suryansh Kumar*, Luc Van Gool, (Oral Presentation)
CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusion
Conference on Robot Learning (CoRL), 2022, Auckland, New Zealand.
Yung-Hsu Yang, Tobias Fischer, Suryansh Kumar, and others
Organic Priors in Non-Rigid Structure from Motion
European Conference on Computer Vision (ECCV), 2022, Tel-Aviv, Israel. [ Oral, Top 2.7% ]
Suryansh Kumar, Luc Van Gool
Learning Online Multi-Sensor Depth Fusion
European Conference on Computer Vision (ECCV), 2022, Tel-Aviv, Israel.
Erik Sandström, Martin Oswald, Suryansh Kumar, and others
Uncertainty Aware Deep Multi-View Photometric Stereo
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022, New Orleans, USA.
Berk Kaya, Suryansh Kumar*, Carlos Oliveira, Vittorio Ferrari, Luc Van Gool
Generative Flows with Invertible Attentions
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022, New Orleans, USA.
Rhea Sukthanker, Zhiwu Huang, Suryansh Kumar, Radu Timofte, Luc Van Gool
Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution
Third Workshop on Neural Architecture Search: 2nd Lightweight NAS Challenge
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022, New Orleans, USA
Yan Wu, Zhiwu Huang, Suryansh Kumar, Rhea Sukthanker, Radu Timofte, Luc Van Gool
A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Seg. of Indoor Scenes
IEEE International Conference on Robotics and Automation (ICRA), 2022, Philadelphia, USA.[ Oral ]
Davide Menini, Suryansh Kumar*, Martin Oswald, Erik Sandstrom, Cristian S, Luc Van Gool
Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo
IEEE Winter Conference on Applications of Computer Vision (WACV), 2022, Hawaii, USA.
Berk Kaya, Suryansh Kumar, Francesco Sarno, Vittorio Ferrari, Luc Van Gool
Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo
IEEE Winter Conference on Applications of Computer Vision (WACV), 2022, Hawaii, USA.
Francesco Sarno, Suryansh Kumar, Berk Kaya, Zhiwu Huang, Vittorio Ferrari, Luc Van Gool
Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021, Nashville, USA.
Berk Kaya, Suryansh Kumar, Carlos Oliveira, Vittorio Ferrari, Luc Van Gool
Neural Architecture Search of SPD Manifold Networks
International Joint Conference on Artificial Intelligence (IJCAI), 2021, Montreal, Canada.
Rhea Sukthanker, Zhiwu Huang, Suryansh Kumar, Erik Goron, Yan Wu, Luc Van Gool
Non-rigid Structure from Motion: Prior-Free Factorization Method Revisited
IEEE Winter Conference on Applications of Computer Vision (WACV), 2020, Colorado, USA.
Suryansh Kumar
Jumping Manifolds: Geometry Aware Dense Non-Rigid Structure from Motion
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, CA, USA. [ Oral ]
Suryansh Kumar
Scalable Dense Non-Rigid Structure from Motion: A Grassmannian Perspective
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, Utah, USA.
Suryansh Kumar, Anoop Cherian, Yuchao Dai, Hongdong Li
Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames
IEEE International Conference on Computer Vision (ICCV), 2017, Venice, Italy.
Suryansh Kumar, Yuchao Dai, Hongdong Li
Non-Rigid Structure from Motion Challenge 2017
Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Honolulu, Hawaii, USA.[ Winner ]
Suryansh Kumar, Yuchao Dai, Hongdong Li
Multi-body Non-rigid Structure from Motion
IEEE International Conference on 3D Vision (3DV), 2016, California, USA.
Suryansh Kumar, Yuchao Dai, Hongdong Li
Markov Random Field based Small Obstacle Discovery over Images
IEEE International Conference on Robotics and Automation (ICRA), 2014, Hong Kong, China.
Suryansh Kumar, Siva Karthik, K Madhava Krishna
Journals and Thesis
Learning Robust Multi-Scale Representation for Neural Radiance Fields from Unposed Images
International Journal of Computer Vision (IJCV), 2024, IF: 19.5[ Invited ]
Nishant Jain, Suryansh Kumar*, Luc Van Gool
Uncertainty-Driven Dense Two-View Structure from Motion
IEEE Robotics and Automation Letter (RAL), 2023, IF: 5.20
Weirong Chen, Suryansh Kumar*, and others
Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields
IEEE Robotics and Automation Letter (RAL), 2022, IF: 5.20
Soomin Lee, Le Chen, Jiahao Wang, Alex Liniger, Suryansh Kumar*, and others
A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Seg. of Indoor Scenes
IEEE Robotics and Automation Letter (RAL), 2022, IF: 5.20
Davide Menini, Suryansh Kumar*, Martin Oswald, Erik Sandstrom, Cristian Sminchisescu, Luc Van Gool
Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene
IEEE Transactions on Pattern and Machine Intelligence (TPAMI), 2021, IF: 17.86
Suryansh Kumar, Yuchao Dai, Hongdong Li
Spatial-Temporal Union of Subspaces for Multi body Non-rigid Structure from Motion
Pattern Recognition Journal, 2017, Elsevier. IF: 7.19
Suryansh Kumar, Yuchao Dai, Hongdong Li
Non-rigid Structure from Motion
Ph.D. Thesis, The Australian National University, 2019. [ Nominated for Best Ph.D. Thesis 2019 ]
Suryansh Kumar
Preprints
Dense Non-Rigid Structure from Motion: A Manifold Viewpoint
arXiv 2020
Suryansh Kumar, Luc Van Gool, Carlos Oliveira, Anoop Cherian, Yuchao Dai, Hongdong Li
Dense Depth Estimation of a Complex Dynamic Scene without Explicit 3D Motion Estimation
arXiv, 2019.
Suryansh Kumar, Ram Srivatsav Ghorakavi, Yuchao Dai, Hongdong Li