88 citations · 318 across the 17 of their papers we have counts for
17 papers
AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels
Javier Tirado-Garín, Alan Savio Paul, Shuai Chen +5
Neural map matchers estimate an image's 3-DoF pose relative to a 2D map. These models are trained on large-scale datasets of geo-referenced images, whose position and heading label…
Scene Coordinate Reconstruction Priors
Wenjing Bian, Axel Barroso-Laguna, Tommaso Cavallari +2
Scene coordinate regression (SCR) models have proven to be powerful implicit scene representations for 3D vision, enabling visual relocalization and structure-from-motion. SCR mode…
ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training
Leonard Bruns, Axel Barroso-Laguna, Tommaso Cavallari +4
Scene coordinate regression (SCR) has established itself as a promising learning-based approach to visual relocalization. After mere minutes of scene-specific training, SCR models…
A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features
Axel Barroso-Laguna, Tommaso Cavallari, Victor Adrian Prisacariu +1
Visually localizing an image, i.e., estimating its camera pose, requires building a scene representation that serves as a visual map. The representation we choose has direct conseq…
Map-Relative Pose Regression for Visual Re-Localization
Shuai Chen, Tommaso Cavallari, Victor Adrian Prisacariu +1
Pose regression networks predict the camera pose of a query image relative to a known environment. Within this family of methods, absolute pose regression (APR) has recently shown…
Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer
Eric Brachmann, Jamie Wynn, Shuai Chen +4
We address the task of estimating camera parameters from a set of images depicting a scene. Popular feature-based structure-from-motion (SfM) tools solve this task by incremental r…
Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses
Eric Brachmann, Tommaso Cavallari, Victor Adrian Prisacariu
Learning-based visual relocalizers exhibit leading pose accuracy, but require hours or days of training. Since training needs to happen on each new scene again, long training times…
Recurrently Estimating Reflective Symmetry Planes from Partial Pointclouds
Mihaela Cătălina Stoian, Tommaso Cavallari
Many man-made objects are characterised by a shape that is symmetric along one or more planar directions. Estimating the location and orientation of such symmetry planes can aid ma…
Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes
Johanna Wald, Torsten Sattler, Stuart Golodetz +2
Long-term camera re-localization is an important task with numerous computer vision and robotics applications. Whilst various outdoor benchmarks exist that target lighting, weather…
Real-Time Highly Accurate Dense Depth on a Power Budget using an FPGA-CPU Hybrid SoC
Oscar Rahnama, Tommaso Cavallari, Stuart Golodetz +5
Obtaining highly accurate depth from stereo images in real time has many applications across computer vision and robotics, but in some contexts, upper bounds on power consumption c…
Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation
Tommaso Cavallari, Luca Bertinetto, Jishnu Mukhoti +2
Many applications require a camera to be relocalised online, without expensive offline training on the target scene. Whilst both keyframe and sparse keypoint matching methods can b…
RSGM: Real-time Raster-Respecting Semi-Global Matching for Power-Constrained Systems
Oscar Rahnama, Tommaso Cavallari, Stuart Golodetz +2
Stereo depth estimation is used for many computer vision applications. Though many popular methods strive solely for depth quality, for real-time mobile applications (e.g. prosthet…
Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade
Tommaso Cavallari, Stuart Golodetz, Nicholas A. Lord +4
Camera pose estimation is an important problem in computer vision. Common techniques either match the current image against keyframes with known poses, directly regress the pose, o…
Collaborative Large-Scale Dense 3D Reconstruction with Online Inter-Agent Pose Optimisation
Stuart Golodetz, Tommaso Cavallari, Nicholas A Lord +3
Reconstructing dense, volumetric models of real-world 3D scenes is important for many tasks, but capturing large scenes can take significant time, and the risk of transient changes…
InfiniTAM v3: A Framework for Large-Scale 3D Reconstruction with Loop Closure
Victor Adrian Prisacariu, Olaf Kähler, Stuart Golodetz +4
Volumetric models have become a popular representation for 3D scenes in recent years. One breakthrough leading to their popularity was KinectFusion, which focuses on 3D reconstruct…
On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation
Tommaso Cavallari, Stuart Golodetz, Nicholas A. Lord +3
Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techn…
Volume-based Semantic Labeling with Signed Distance Functions
Tommaso Cavallari, Luigi Di Stefano
Research works on the two topics of Semantic Segmentation and SLAM (Simultaneous Localization and Mapping) have been following separate tracks. Here, we link them quite tightly by…