Fraunhofer Institute for Telecommunications,
Heinrich-Hertz-Institut, HHI
Video Communication and ApplicationsNewsTechnologies and SolutionsResearch GroupsProjectsPublicationsPeople and Contact

Fangwen Shu

Biography

Fangwen Shu joined the Multimedia Communications Group at Fraunhofer HHI (Heinrich Hertz Institute) on March 2023. He is currently working on Immersive Video Technologies such as cutting-edge neural rendering algorithms and efficient streaming for 3D volumetric video synthesis. He is also supporting the standardization activities for immersive streaming.

From 2019-2023, he worked as a computer vision researcher at the Department Augmented Vision, DFKI (German Research Centre for Artificial Intelligence) GmbH, where he specializes in real-time 3D reconstruction technologies and learning-based scene understanding, especially familiar with feature-based visual SLAM (Simultaneous Localization and Mapping) systems, Structure-from-Motion (SfM) and Multi-View Stereo (MVS) algorithms.

Before that, he received his M.Sc. degree (GeoEngine/Geoinformatics, 2019) from Universität Stuttgart, Germany, and his B.Eng. degree (Photogrammetry and Remote Sensing, 2016) from Wuhan University, China.

Google Scholar

Google Scholar Profile

Publications

Previous conference contributions:

  • Structure PLP-SLAM: Efficient Sparse Mapping and Localization using Point, Line and Plane for Monocular, RGB-D and Stereo Cameras
    Fangwen Shu, Jiaxuan Wang, Alain Pagani, Didier Stricker
    IEEE International Conference on Robotics and Automation (ICRA), 2023
     
  • PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB Image
    Yaxu Xie, Fangwen Shu, Jason Rambach, Alain Pagani, Didier Stricker
    British Machine Vision Conference (BMVC), 2021
  • Visual SLAM with Graph-Cut Optimized Multi-Plane Reconstruction
    Fangwen Shu, Yaxu Xie, Jason Rambach, Alain Pagani, Didier Stricker
    IEEE International Symposium on Mixed and Augmented Reality (ISMAR, poster), 2021
     
  • PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN
    Yaxu Xie, Jason Rambach, Fangwen Shu, Didier Stricker
    IEEE International Conference on Robotics and Automation (ICRA), 2021
     
  • SLAM in the Field: An Evaluation of Monocular Mapping and Localization on Challenging Dynamic Agricultural Environment
    Fangwen Shu, Paul Lesur, Yaxu Xie, Alain Pagani, Didier Stricker
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021