Danda Pani Paudel
Computer Vision Lab, ETH Zurich

I am a researcher at the Computer Vision Lab, ETH Zurich, working with Prof. Luc Van Gool. My research interests include Computer Vision, Visual-SLAM, Unsupervised Learning, and Optimization Methods. I received my Doctoral degree (PhD) in 2015, and a Master's degree in computer vision in 2012, form University of Bourgogne, France. I also worked as a research scholar at University of Strasbourg, France, form 2013 to 2015, while devising global and local methods for 2D-3D registration problems.

Computer Vision

Visual SLAM

Unsupervised Learning

Optimization Methods

Research Topics

  • Show All
  • 3D Vision
  • Learning for Vision

Registration

Consensus Maximization of Correspondences

Camera Autocalibration

Robust and Global Methods

SLAM

Static and Dynamic Scene Reconstruction and Understanding

Image Retrieval

Image Features for Camera Localization and Navigation

GANs

Image and Video Generative Adversarial Networks

Image Understanding

Multi-tasking and Domain Generalization

Selected Publications

Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU.

Shipra Jain, Danda Pani Paudel, Martin Danelljan, and Luc Van Gool. In IEEE International Conference on Computer Vision (ICCV'21), Accepted, 2021. [PDF] [Code]

Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images.

Yigit Baran Can, Alexander Liniger, Danda Pani Paudel, and Luc Van Gool. In IEEE International Conference on Computer Vision (ICCV'21), Accepted, 2021.

Learning Target Candidate Association to Keep Track of What Not to Track.

Christoph Mayer, Martin Danelljan, Danda Pani Paudel, and Luc Van Gool. In IEEE International Conference on Computer Vision (ICCV'21), Accepted, 2021. [PDF] [Code]

Task Switching Network for Multi-task Learning.

Guolei Sun, Thomas Probst, Danda Pani Paudel, Nikola Popovic, Menelaos Kanakis, Dengxin Dai, and Luc Van Gool. In IEEE International Conference on Computer Vision (ICCV'21), Accepted, 2021.

Unsupervised Compound Domain Adaptation for Face Anti-Spoofing.

Ankush Panwar, Pratyush Singh, Suman Saha, Danda Pani Paudel, and Luc Van Gool. In IEEE International Conference on Automatic Face and Gesture Recognition (FG'21), Accepted, 2021. [PDF]

CompositeTasking: Understanding Images by Spatial Composition of Tasks.

Nikola Popovic, Danda Pani Paudel, Thomas Probst, Guolei Sun, and Luc Van Gool. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'21), 2021. [PDF] [Code]

GANmut: Learning Interpretable Conditional Space for a Gamut of Emotions.

Stefano D'Apolito, Danda Pani Paudel, Zhiwu Huang, Andrés Romero, and Luc Van Gool. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'21), 2021. [PDF] [Code]

Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation.

Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis, Yuhua Chen, Stamatios Georgoulis, and Luc Van Gool. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'21), 2021. [PDF] [Code]

Efficient Conditional GAN Transfer with Knowledge Propagation across Classes.

Mohamad Shahbazi, Zhiwu Huang, Danda Pani Paudel, Ajad Chhatkuli, and Luc Van Gool. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'21), 2021. [PDF] [Code]

Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation.

Gong, Rui, Yuhua Chen, Danda Pani Paudel, Yawei Li, Ajad Chhatkuli, Wen Li, Dengxin Dai, and Luc Van Gool. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'21), 2021. [PDF]

Analogical Image Translation for Fog Generation.

Rui Gong, Dengxin Dai, Yuhua Chen, Wen Li, Danda Pani Paudel, Luc Van Gool. In AAAI Conference on Artificial Intelligence (AAAI'21), 2021. [PDF]

Moving Object Detection by 3D Flow Field Analysis.

Cansen Jiang, Danda Pani Paudel, David Fofi, Yohan Fougerolle, and Cédric Demonceaux. In IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2021. [PDF]

Facial Emotion Recognition with Noisy Multi-task Annotations.

Siwei Zhang, Zhiwu Huang, Danda Pani Paudel, and Luc Van Gool. In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV'21), 2021. [PDF] [Code]

Soft Contrastive Learning for Visual Localization.

Janine Thoma, Danda Pani Paudel, Luc Van Gool. In Advances in Neural Information Processing Systems (NeurIPS'20), 2020. [PDF] [Code]

Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets.

Clara Fernandez-Labrador, Ajad Chhatkuli, Danda Pani Paudel, Jose J Guerrero, Cédric Demonceaux, Luc Van Gool. In European Conference on Computer Vision (ECCV'20), 2020. [PDF] [Code]

Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing.

Suman Saha, Wenhao Xu, Menelaos Kanakis, Stamatios Georgoulis, Yuhua Chen, Danda Pani Paudel, Luc Van Gool. In IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW'20, Best Paper Award), 2020. [PDF]

Geometrically Mappable Image Features.

Janine Thoma, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool. In IEEE Robotics and Automation Letters (RA-L), 2020. [PDF] [Code]

Convex Relaxations for Consensus and Non-Minimal Problems in 3D Vision.

Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool. In IEEE International Conference on Computer Vision (ICCV'19), 2019. [PDF] [Code]

What Correspondences Reveal about Unknown Camera and Motion Models?

Thomas Probst, Ajad Chhatkuli, Danda Pani Paudel, Luc Van Gool. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'19, Oral), 2019. [PDF] [Code]

Unsupervised Learning of Consensus Maximization for 3D Vision.

Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'19), 2019. [PDF] [Code]

Image-based Navigation using Visual Features and Map.

Janine Thoma, Danda Pani Paudel, Ajad Chhatkuli, Thomas Probst, Luc Van Gool. In IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR'19), 2019. [PDF] [Code]

Sliced Wasserstein Generative Models.

Jiqing Wu, Zhiwu Huang, Wen Li, Danda Pani Paudel, Janine Thoma, Luc Van Gool. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'19), 2019. [PDF] [Code]

Learning Feature Representations for Look-Alike Images.

Ayca Takmaz, Thomas Probst, Danda Pani Paudel, Luc Van Gool. In IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW'19), 2019. [PDF]

Incremental Non-Rigid SfM with Unknown Focal Length.

Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool. In European Conference on Computer Vision (ECCV'18), 2018. [PDF] [Code]

Model-free Consensus Maximization for Non-Rigid Shapes.

Thomas Probst, Ajad Chhatkuli, Danda Pani Paudel, Luc Van Gool. In European Conference on Computer Vision (ECCV'18), 2018. [PDF] [Code]

Sampling Algebraic Varieties for Robust Camera Autocalibration.

Danda Pani Paudel and Luc Van Gool. In European Conference on Computer Vision (ECCV'18), 2018. [PDF]

Robust and Optimal Registration of Image Sets and Structured Scenes via Sum-of-Squares Polynomials.

Danda Pani Paudel, Adlane Habed, Cédric Demonceaux, and Pascal Vasseur. International Journal of Computer Vision (IJCV, Spl. Issue, Best of ICCV). p.1-22, 2018. [PDF] [Code]

Consensus Maximization for Semantic Region Correspondences.

Pablo Speciale, Danda Pani Paudel, Martin R. Oswald, Hayko Riemenschneider, Luc V. Gool, and Marc Pollefeys. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'18, Spotlight ), 2018. [PDF] [Code] [Project Page]

Covariance Pooling for Facial Expression Recognition.

Acharya, Dinesh, Zhiwu Huang, Danda Pani Paudel, and Luc Van Gool. Differential Geometry in Computer Vision and Machine Learning (DiffCVML). In Conjunction with Computer Vision and Pattern Recognition (CVPRW'18), 2018. [PDF] [Code]

2D–3D synchronous/asynchronous camera fusion for visual odometry.

Danda Pani Paudel, Cédric Demonceaux, Adlane Habed, and Pascal Vasseur. Autonomous Robots (AR). p.1-15, 2018. [PDF]

Static and Dynamic Objects Analysis as a 3D Vector Field.

Cansen Jiang, Danda Pani Paudel, Yohan Fougerolle, David Fofi, and Cédric Demonceaux. In International Conference on 3D Vision (3DV'17, Oral), 2017. [PDF]

Optimal Transformation Estimation with Semantic Cues.

Danda Pani Paudel, Adlane Habed, and Luc Van Gool. In IEEE International Conference on Computer Vision (ICCV'17), 2017. [PDF] .

VarCity – the Video: the Struggles and Triumphs of Leveraging Fundamental Research Results in a Graphics Video Production.

Kenneth Vanhoey, Carlos E Oliveira, Hayko Riemenschneider, Andras B Szomoru, Santiago Manen, Danda Pani Paudel, Michael Gygli, Nikolay Kobyshev, Till Kroeger, Dengxin Dai, and Luc V Gool. In Proceedings of SIGGRAPH Talks (SIGGRAPH’17), 2017. [PDF] [Project Page]

Incomplete 3D Motion Trajectory Segmentation and 2D-to-3D Label Transfer for Dynamic Scene Analysis.

Cansen Jiang, Danda Pani Paudel, Yohan Fougerolle, David Fofi, and Cédric Demonceaux. In IEEE/RSJ Conference on Intelligent Robots and Systems (IROS'17), 2017. [PDF] [Code]

Consensus Maximization with Linear Matrix Inequality Constraints.

Pablo Speciale, Danda Pani Paudel, Martin R Oswald, Till Kroeger, Luc V Gool, and Marc Pollefeys. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17), 2017. [PDF] [Code] [Project Page]

Static-map and Dynamic Object Reconstruction in Outdoor Environments using 3D Motion Segmentation.

Cansen Jiang, Danda Pani Paudel, Yohan Fougerolle, David Fofi, and Cédric Demonceaux. In IEEE Robotics and Automation Letters (RA-L), p.324-331, 2016. [PDF]

Robust and Optimal SoS-based Point-to-Plane Registration of Image Sets and Structured Scenes.

Danda Pani Paudel, Adlane Habed, Cédric Demonceaux, and Pascal Vasseur. In IEEE International Conference on Computer Vision (ICCV'15, Oral), p.2048-2056, 2015. [PDF] [Code]

LMI-based 2D-3D Registration: Uncalibrated Images to Euclidean Scene.

Danda Pani Paudel, Adlane Habed, Cédric Demonceaux, and Pascal Vasseur. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15), p.4494-4502, 2015. [PDF] [Code]

2D-3D camera fusion for visual odometry in outdoor environments.

Danda Pani Paudel, Cédric Demonceaux, Adlane Habed, and Pascal Vasseur. In IEEE/RSJ Conference on Intelligent Robots and Systems (IROS'14), p.157-162, 2014. [PDF]

Efficient pruning LMI conditions for Branch-and-Prune Rank and Chirallity-Constrained Estimation of the Dual Absolute Quadric.

Adlane Habed, Danda Pani Paudel, Cédric Demonceaux, and David Fofi. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'14), p.493-500, 2014. [PDF] [Code]

Teaching

Teaching Assistant, ETH Zurich

September 2017 – March 2019

Switzerland Master’s level labs and tutorials in Computer Vision.

Teaching Assistant, University of Bourgogne

November 2012 – October 2015

Centre Universitaire CondorcetMaster’s level lectures in Computer Vision, 3D Vision, C++ programming, and Digital signal processing.

Student Supervision

2014 - Present

Co-supervisor of more than Twenty Master’s theses, more than Twenty Master’s semester projects, and four research internships.

Services

Administrative Roles

Area Co-chair for Multimedia and Vision track, IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) 2018.

Leadership Roles

Reviewer for various editions of Vision and Robotics related Journal and Conferences: IJCV, CVPR, ICRA, IROS, ICCV, ECCV, PR, ICIP, ICPR, ITSM, and IET-CV.

Journals and Conferences

Organizing committee member of the AI winter schools in Nepal, 2018 and 2019.

Others

Co-founder of a non-profit organization, Nepal Applied Mathematics and Informatics Institute for Research.

Projects

Varcity

VarCity was an ERC research project at the Computer Vision Lab, ETH Zurich. Its goal was to obtain 3D reconstructions using only images, together with the understanding of city static composition, dynamic movement, and virtual life on social media.

Read More

Encore

The main objective of ENCORE is to increase the share of renovated stock by providing effective and affordable BIM for renovation works. The Computer Vision Lab is involve in providing the required BIM model using only the visual data.

Read More

NAAMII

NAAMII is a profit-not-distributing research organization which plays a pivotal role in building a strong foundation of research and support the ecosystem of higher education and innovation in the field of informatics, applied mathematics and AI.

Read More

Awards & Scholarships

Contact

Your Message has been sent!

Something went wrong, go back and try again!

  • Address

    Computer Vision Laboratory
    ETF C112, Sternwartstrasse 7
    8092 Zürich, Switzerland

  • Phone

    +41 44 63 22774

  • Email

    paudel@vision.ee.ethz.ch