7 papers · 1 filter
PolyLayout: Multi-room Manhattan Layout Estimation
Gustav Hanning, Shaohui Liu, Rémi Pautrat +5
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…
LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching
Aidyn Ubingazhibov, Rémi Pautrat, Iago Suárez +3
Lines and points are complementary local features, whose combination has proven effective for applications such as SLAM and Structure-from-Motion. The backbone of these pipelines a…
Benchmarking Egocentric Visual-Inertial SLAM at City Scale
Anusha Krishnan, Shaohui Liu, Paul-Edouard Sarlin +6
Precise 6-DoF simultaneous localization and mapping (SLAM) from onboard sensors is critical for wearable devices capturing egocentric data, which exhibits specific challenges, such…
Relative Pose Estimation through Affine Corrections of Monocular Depth Priors
Yifan Yu, Shaohui Liu, Rémi Pautrat +2
Monocular depth estimation (MDE) models have undergone significant advancements over recent years. Many MDE models aim to predict affine-invariant relative depth from monocular ima…
Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization
Siyan Dong, Shuzhe Wang, Shaohui Liu +4
Visual localization aims to determine the camera pose of a query image relative to a database of posed images. In recent years, deep neural networks that directly regress camera po…
Robust Incremental Structure-from-Motion with Hybrid Features
Shaohui Liu, Yidan Gao, Tianyi Zhang +4
Structure-from-Motion (SfM) has become a ubiquitous tool for camera calibration and scene reconstruction with many downstream applications in computer vision and beyond. While the…