5 papers
EPO: Boosting 3D Foundation Models with Edge-based Pose Optimization
Mattia D'Urso, Christian Sormann, Mattia Rossi +1
We introduce \textbf{Edge-based Pose Optimization (EPO)}, a trackless geometric optimization framework specifically designed to boost the Structure-from-Motion reconstructions gene…
A Streamlined Attention-Based Network for Descriptor Extraction
Mattia D'Urso, Emanuele Santellani, Christian Sormann +3
We introduce SANDesc, a Streamlined Attention-Based Network for Descriptor extraction that aims to improve on existing architectures for keypoint description. Our descriptor networ…
Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding
Yuchen Rao, Stefan Ainetter, Sinisa Stekovic +2
High-level 3D scene understanding is essential in many applications. However, the challenges of generating accurate 3D annotations make development of deep learning models difficul…
GMM-IKRS: Gaussian Mixture Models for Interpretable Keypoint Refinement and Scoring
Emanuele Santellani, Martin Zach, Christian Sormann +3
The extraction of keypoints in images is at the basis of many computer vision applications, from localization to 3D reconstruction. Keypoints come with a score permitting to rank t…
PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction
Sinisa Stekovic, Arslan Artykov, Stefan Ainetter +2
We propose PyTorchGeoNodes, a differentiable module for reconstructing 3D objects and their parameters from images using interpretable shape programs. Unlike traditional CAD model…