154 citations · 243 across the 27 of their papers we have counts for
5 papers · 2 filters
Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Clouds
Shenglan Du, Nail Ibrahimli, Jantien Stoter +2
Feedforward fully convolutional neural networks currently dominate in semantic segmentation of 3D point clouds. Despite their great success, they suffer from the loss of local info…
How do Cross-View and Cross-Modal Alignment Affect Representations in Contrastive Learning?
Thomas M. Hehn, Julian F. P. Kooij, Dariu M. Gavrila
Various state-of-the-art self-supervised visual representation learning approaches take advantage of data from multiple sensors by aligning the feature representations across views…
SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation
Ted Lentsch, Zimin Xia, Holger Caesar +1
This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area…
Visual Cross-View Metric Localization with Dense Uncertainty Estimates
Zimin Xia, Olaf Booij, Marco Manfredi +1
This work addresses visual cross-view metric localization for outdoor robotics. Given a ground-level color image and a satellite patch that contains the local surroundings, the tas…
DDL-MVS: Depth Discontinuity Learning for MVS Networks
Nail Ibrahimli, Hugo Ledoux, Julian Kooij +1
Traditional MVS methods have good accuracy but struggle with completeness, while recently developed learning-based multi-view stereo (MVS) techniques have improved completeness exc…