From the 1 of 5 linked papers with an AI index.
5 papers
SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment
Saad Ejaz, Miguel Fernandez-Cortizas, Javier Civera +2
The paper introduces SUFLECA, a weakly‑supervised framework that learns geometry‑aware features from large image collections to align CAD models to single RGB images, enabling zero…
Passage-Aware Structural Mapping for RGB-D Visual SLAM
Ali Tourani, Miguel Fernandez-Cortizas, Saad Ejaz +4
Doorways and passages are critical structural elements for indoor robot navigation, yet they remain underexplored in modern Visual SLAM (VSLAM) frameworks. This paper presents a pa…
Situationally-aware Path Planning Exploiting 3D Scene Graphs
Saad Ejaz, Marco Giberna, Muhammad Shaheer +5
3D Scene Graphs integrate both metric and semantic information, yet their structure remains underutilized for improving path planning efficiency and interpretability. In this work,…
vS-Graphs: Tightly Coupling Visual SLAM and 3D Scene Graphs Exploiting Hierarchical Scene Understanding
Ali Tourani, Saad Ejaz, Hriday Bavle +4
Current Visual Simultaneous Localization and Mapping (VSLAM) systems often struggle to create maps that are both semantically rich and easily interpretable. While incorporating sem…
Category-level Meta-learned NeRF Priors for Efficient Object Mapping
Saad Ejaz, Hriday Bavle, Laura Ribeiro +2
In 3D object mapping, category-level priors enable efficient object reconstruction and canonical pose estimation, requiring only a single prior per semantic category (e.g., chair,…