no code implementations • 23 Nov 2023 • Soonbin Lee, Fangwen Shu, Yago Sanchez, Thomas Schierl, Cornelius Hellge
Furthermore, to achieve a higher level of sparsity, we propose using an entropy parameterization technique for the frequency domain, specifically for DCT coefficients of the feature-grid.
1 code implementation • 13 Jul 2022 • Fangwen Shu, Jiaxuan Wang, Alain Pagani, Didier Stricker
One of the biggest challenges in parallel tracking and mapping with a monocular camera is to keep the scale consistent when reconstructing the geometric primitives.
2 code implementations • 21 Oct 2021 • Yaxu Xie, Fangwen Shu, Jason Rambach, Alain Pagani, Didier Stricker
Piece-wise 3D planar reconstruction provides holistic scene understanding of man-made environments, especially for indoor scenarios.
1 code implementation • 9 Aug 2021 • Fangwen Shu, Yaxu Xie, Jason Rambach, Alain Pagani, Didier Stricker
This paper presents a semantic planar SLAM system that improves pose estimation and mapping using cues from an instance planar segmentation network.
no code implementations • 29 Mar 2021 • Yaxu Xie, Jason Rambach, Fangwen Shu, Didier Stricker
Our model employs a variant of a fast single-stage CNN architecture to segment plane instances.
no code implementations • 2 Nov 2020 • Fangwen Shu, Paul Lesur, Yaxu Xie, Alain Pagani, Didier Stricker
This paper demonstrates a system capable of combining a sparse, indirect, monocular visual SLAM, with both offline and real-time Multi-View Stereo (MVS) reconstruction algorithms.