18 papers · 1 filter
Unified and Efficient Point-Line Local Features
François Costa, Raphael Kreft, Eckhard Goedeke +6
Multi-view computer vision pipelines typically rely on accurate sparse keypoints and robust descriptors. While incorporating line features has shown clear benefits for matching and…
PolyLayout: Multi-room Manhattan Layout Estimation
Gustav Hanning, Shaohui Liu, Rémi Pautrat +3
Estimating room layouts from multi-view imagery is a core task for indoor scene understanding. Existing methods are typically limited either by poor generalization to new datasets…
VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion
Zador Pataki, Paul-Edouard Sarlin, Marc Pollefeys
Accurately recovering the camera's calibration and metric poses for any unconstrained video would unlock large-scale training data for navigation and scene understanding. The domin…
Unblur-SLAM: Dense Neural SLAM for Blurry Inputs
Qi Zhang, Denis Rozumny, Francesco Girlanda +4
We propose Unblur-SLAM, a novel RGB SLAM pipeline for sharp 3D reconstruction from blurred image inputs. In contrast to previous work, our approach is able to handle different type…
DROID-SLAM in the Wild
Moyang Li, Zihan Zhu, Marc Pollefeys +1
We present a robust, real-time RGB SLAM system that handles dynamic environments by leveraging differentiable Uncertainty-aware Bundle Adjustment. Traditional SLAM methods typicall…
RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer
Jiuming Liu, Guangming Wang, Zhe Liu +7
Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale LiDAR registration methods has been rarely explored before. Challe…