10 papers · 1 filter
OTT3R: Multi-View 3D Reconstruction and Fast Dataset Generation at 1% Compute
Brandon Leblanc, Charalambos Poullis
Feed-forward 3D reconstruction models have achieved impressive performance by scaling model and dataset size, but their cost excludes most research groups and precludes edge deploy…
SAGE-OR: Semi-supervised Adaptive Scene Graph Generation for Operating Rooms
Brandon Leblanc, Charalambos Poullis
Current surgical scene graph generation methods depend on dense multi-modal supervision and specialized hardware (synchronized RGB-D sensors, calibration rigs), making dataset cons…
Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware
Brandon Leblanc, Charalambos Poullis
While multi-view 3D reconstruction has shifted toward large-scale foundation models capable of inferring globally consistent geometry, their reliance on massive computational clust…
Extreme Views: 3DGS Filter for Novel View Synthesis from Out-of-Distribution Camera Poses
Damian Bowness, Charalambos Poullis
When viewing a 3D Gaussian Splatting (3DGS) model from camera positions significantly outside the training data distribution, substantial visual noise commonly occurs. These artifa…
Fast Self-Supervised depth and mask aware Association for Multi-Object Tracking
Milad Khanchi, Maria Amer, Charalambos Poullis
Multi-object tracking (MOT) methods often rely on Intersection-over-Union (IoU) for association. However, this becomes unreliable when objects are similar or occluded. Also, comput…
Depth-Aware Scoring and Hierarchical Alignment for Multiple Object Tracking
Milad Khanchi, Maria Amer, Charalambos Poullis
Current motion-based multiple object tracking (MOT) approaches rely heavily on Intersection-over-Union (IoU) for object association. Without using 3D features, they are ineffective…
DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation
Amin Karimi, Charalambos Poullis
Few-shot semantic segmentation (FSS) aims to enable models to segment novel/unseen object classes using only a limited number of labeled examples. However, current FSS methods freq…
Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagery
Yeshwanth Kumar Adimoolam, Charalambos Poullis, Melinos Averkiou
Extraction of building footprint polygons from remotely sensed data is essential for several urban understanding tasks such as reconstruction, navigation, and mapping. Despite sign…
Neural Real-Time Recalibration for Infrared Multi-Camera Systems
Benyamin Mehmandar, Reza Talakoob, Charalambos Poullis
Currently, there are no learning-free or neural techniques for real-time recalibration of infrared multi-camera systems. In this paper, we address the challenge of real-time, highl…
HydroVision: LiDAR-Guided Hydrometric Prediction with Vision Transformers and Hybrid Graph Learning
Naghmeh Shafiee Roudbari, Ursula Eicker, Charalambos Poullis +1
Hydrometric forecasting is crucial for managing water resources, flood prediction, and environmental protection. Water stations are interconnected, and this connectivity influences…