Lightglue: Local feature matching at light speed
P Lindenberger, PE Sarlin… - Proceedings of the …, 2023 - openaccess.thecvf.com
We introduce LightGlue, a deep neural network that learns to match local features across
images. We revisit multiple design decisions of SuperGlue, the state of the art in sparse …
images. We revisit multiple design decisions of SuperGlue, the state of the art in sparse …
SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM
Dense simultaneous localization and mapping (SLAM) is crucial for robotics and augmented
reality applications. However current methods are often hampered by the non-volumetric or …
reality applications. However current methods are often hampered by the non-volumetric or …
An outlook into the future of egocentric vision
What will the future be? We wonder! In this survey, we explore the gap between current
research in egocentric vision and the ever-anticipated future, where wearable computing …
research in egocentric vision and the ever-anticipated future, where wearable computing …
Probabilistic human mesh recovery in 3d scenes from egocentric views
Automatic perception of human behaviors during social interactions is crucial for AR/VR
applications, and an essential component is estimation of plausible 3D human pose and …
applications, and an essential component is estimation of plausible 3D human pose and …
Long-term visual localization with mobile sensors
S Yan, Y Liu, L Wang, Z Shen, Z Peng… - Proceedings of the …, 2023 - openaccess.thecvf.com
Despite the remarkable advances in image matching and pose estimation, image-based
localization of a camera in a temporally-varying outdoor environment is still a challenging …
localization of a camera in a temporally-varying outdoor environment is still a challenging …
Snap: Self-supervised neural maps for visual positioning and semantic understanding
Semantic 2D maps are commonly used by humans and machines for navigation purposes,
whether it's walking or driving. However, these maps have limitations: they lack detail, often …
whether it's walking or driving. However, these maps have limitations: they lack detail, often …
Multiway Point Cloud Mosaicking with Diffusion and Global Optimization
We introduce a novel framework for multiway point cloud mosaicking (named Wednesday)
designed to co-align sets of partially overlapping point clouds--typically obtained from 3D …
designed to co-align sets of partially overlapping point clouds--typically obtained from 3D …
Deepmapping2: Self-supervised large-scale lidar map optimization
LiDAR mapping is important yet challenging in self-driving and mobile robotics. To tackle
such a global point cloud registration problem, DeepMapping converts the complex map …
such a global point cloud registration problem, DeepMapping converts the complex map …
EgoGen: An Egocentric Synthetic Data Generator
Understanding the world in first-person view is fundamental in Augmented Reality (AR). This
immersive perspective brings dramatic visual changes and unique challenges compared to …
immersive perspective brings dramatic visual changes and unique challenges compared to …
Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction
We tackle the problem of estimating a Manhattan frame, ie three orthogonal vanishing
points, and the unknown focal length of the camera, leveraging a prior vertical direction. The …
points, and the unknown focal length of the camera, leveraging a prior vertical direction. The …