Fraunhofer Institute for Telecommunications,
Heinrich Hertz Institute, HHI
Vision & Imaging Technologies

Niklas Gard

Research Associate Computer Vision & Graphics Group

Contact

Mailing address:
Fraunhofer HHI
Einsteinufer 37
10587 Berlin
Germany

Visitor address:
Room 04-12
Salzufer 15/16
10587 Berlin

Phone: +49-(0)30-31002-191
E-mail:

Biography

Niklas Gard is a research associate in the Computer Vision & Graphics Group at Fraunhofer Heinrich Hertz Institute. He graduated in Computervisualistik at the University of Koblenz-Landau with a Master of Science (M.Sc.) degree in 2015. From 2012 to 2015 he worked as a student assistant in the Research Group Artificial Intelligence at the University of Koblenz-Landau. From March 2016 to April 2017 he has been part of the Capture & Display Systems Group at Fraunhofer HHI. From April 2017 to March 2020 he has also been a member of the Visual Computing Research Group at the Humboldt University of Berlin. Currently, he is involved in the collaborative research project BIMKIT and EConoM. Before that, he participated in the research projects 3DInMed, Easy Cohmo, and DigitalTWIN.

News

27.09.2024

Our paper "SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments" is accepted as ECCV 2024 paper with oral presentation.

16.04.2024

Our new preprint "SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments" is available on arXiv. The source code is available at GitHub.

04.04.2023

We are happy that our paper "X-maps: Direct Depth Lookup for Event-based Structured Light Systems" has been accepted at the CVPR 2023 Workshop on Event-based Vision. The source code is available at GitHub.

16.01.2023

The source code for our BMVC 2022 paper "CASAPose: Class-Adaptive and Semantic-Aware Multi-Object Pose Estimation" is available at GitHub now.

Publications

2024

  • N. Gard, A. Hilsmann, P. Eisert,,
    SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments, European Conference on Computer Vision (ECCV), October 2024. [arXiv] [Code]
  • A. Aziz, N. Gard, P. Eisert, M. König, A. Hilsmann,
    Verwendung von Deep Learning Methoden zur Erkennung und Verfolgung von Objekten bei Inspektions- und Montageaufgaben, Book Chapter, Künstliche Intelligenz im Bauwesen: Grundlagen und Anwendungsfälle, May 2024, doi:10.1007/978-3-658-42796-2_11  . [Book]

2023

  • N. Gard, A. Cambeiro Barreiro,
    Towards Automated Digital Building Model Generation from Floorplans and On-Site Images, 34th Forum Bauinformatik, September 2023, doi: 10.13154/294-10132  . [PDF]
  • W. Morgenstern, N. Gard, S. Baumann, A. Hilsmann, P. Eisert,
    X-maps: Direct Depth Lookup for Event-based Structured Light Systems, CVPR 2023 Workshop on Event-based Vision, June 2023, doi: 10.1109/CVPRW59228.2023.00418  . [PDF] [Code] [Workshop]
  • P. Chojecki, D. Strazdas, D. Przewozny, N. Gard, D. Runde, N. Hoerner, A. Al-Hamadi, P. Eisert, S. Bosse,
    Assessing the Value of Multimodal Interfaces: A Study on Human–Machine Interaction in Weld Inspection Workstations, MDPI Sensors, vol. 23, no. 11, May 2023, doi: 10.3390/s23115043  . [PDF] [Video]

2022

  • N. Gard, A. Hilsmann, P. Eisert,
    CASAPose: Class-Adaptive and Semantic-Aware Multi-Object Pose Estimation, Proc. 33rd British Machine Vision Conference (BMVC), Nov. 2022, arXiv: 2210.05318  . [PDF] [Code] [BMVC] [Video]
  • D. Przewozny, D. Runde, N. Hoerner, N. Gard, S. Bosse, P. Chojecki,
    Comparison of Uni-and Multimodal Interfaces for Spatial Interaction, Proc. 2022 ACM Symposium on Spatial User Interaction (SUI), Dec. 2022, doi: 10.1145/3565970.3567708  . [PDF]
  • N. Gard, A. Hilsmann, P. Eisert,
    Combining Local and Global Pose Estimation for Precise Tracking of Similar Objects, Proc. 17th International Conference on Computer Vision Theory and Applications (VISAPP), Feb. 2022, doi: 10.5220/0010882700003124  . [PDF] [Video]

2021

  • M. Janik, N. Gard, A. Hilsmann, P. Eisert,
    Zero in on Shape: A Generic 2D-3D Instance Similarity Metric learned from Synthetic Data, Proc. 2021 IEEE Interational Conference on Image Processing (ICIP), Sept. 2021, doi: 10.1109/ICIP42928.2021.9506436  . [PDF] [Testdata]

2019

  • N. Gard, A. Hilsmann, P. Eisert,
    Projection Distortion-based Object Tracking in Shader Lamp Scenarios, IEEE Transactions on Visualization and Computer Graphics, vol. 25, no. 11, pp. 3105-3113, Nov. 2019, doi: 10.1109/TVCG.2019.2932223  . [PDF] [Poster]

2018

  • J.-C. Rosenthal, N. Gard, A. Schneider, P. Eisert,
    Microscopic image-based determination of stapes prosthesis length, CARS 2018-Computer Assisted Radiology and Surgery Proceedings of the 32st International Congress and Exhibition, Berlin, Germany, June 2018, doi: 10.1007/s11548-018-1766-y  . [PDF] [ISCAS Best Paper Award]
  • N. Gard, P. Eisert,
    Markerless Closed-Loop Projection Plane Tracking for Mobile Projector-Camera Systems, Proc. 2018 IEEE Interational Conference on Image Processing (ICIP), Athens, Greece, Oct. 2018, doi: 10.1109/ICIP.2018.8451038  . [PDF] [Poster]

2017

  • J.-C. Rosenthal, N. Gard, P. Eisert,
    Kalibrierung stereoskopischer Systeme für medizinische Messaufgaben, CURAC 2017 Tagungsband: 16. Jahrestagung der Deutschen Gesellschaft für Computer- und Roboterassistierte Chirurgie (CURAC), Hannover, Germany, pp. 159-161, Oct. 2017. [PDF] [INFO]

2016

  • J.-C. Rosenthal, N. Gard, P. Kauff,
    Depth-Based Quality Control for Medical Applications, SID-ME Fall Meeting 2016, Berlin, Germany, p. 13, Nov. 2016.

Other Contributions

2021

  • N. Gard,
    6D Object Pose Estimation for Augmented Reality Assistance, Talk at Photonics Days Berlin Brandenburg 2021 - Sensor Al - a key for a new generation of sensor systems, Berlin, Germany, Oct. 2021. [Info]
  • N. Gard,
    Multi Object 6D Pose Estimation for AR-Assistance, Talk at Summer School on Video Coding and Processing – SVCP202(0)1, Berlin, Germany, July 2021. [INFO] [Slides]
  • N. Gard, S. Renault, I. Feldmann, P. Eisert, G. Matl, P. Kopriwa, F. Schmid
    XR-Technologien im Bauwesen, Smart Design, Smart Construction, Smart Operation, Begleitforschung Smart Service Welt II, Institut für Innovation und Technik (iit), April 2021. [INFO] [PDF]

2019

  • J.-C. Rosenthal, Z. Hu, N. Gard, P. Eisert,
    Endoscopic Vision Challenge - Stereo Correspondence and Reconstruction of Endoscopic Data (SCARED), organized by Intuitive Surgical, 22nd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Shenzhen, China, October 2019, Runners-Up Award. [INFO] [arXiv Paper (2020)]

2017

  • N. Gard, S. Jurk, A. Schneider, P. Kauff, P. Eisert, J.-C. Rosenthal,
    New Tools for Digital Surgical Microscopy, Talk at CARS (Computer Assisted Radiology and Surgery) congress, Barcelona, Spain, Jun. 2017.