5 papers
Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesis
Federico Lincetto, Gianluca Agresti, Mattia Rossi +2
Neural rendering techniques allow for accurate reconstruction of the geometry and color appearance of 3D scenes. Some methods have extended their use to additional imaging modaliti…
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…
TerraSky3D: Multi-View Reconstructions of European Landmarks in 4K
Mattia D'Urso, Yuxi Hu, Christian Sormann +2
Despite the growing need for data of more and more sophisticated 3D reconstruction pipelines, we can still observe a scarcity of suitable public datasets. Existing 3D datasets are…
MultimodalStudio: A Heterogeneous Sensor Dataset and Framework for Neural Rendering across Multiple Imaging Modalities
Federico Lincetto, Gianluca Agresti, Mattia Rossi +1
Neural Radiance Fields (NeRF) have shown impressive performances in the rendering of 3D scenes from arbitrary viewpoints. While RGB images are widely preferred for training volume…
Exploiting Multiple Priors for Neural 3D Indoor Reconstruction
Federico Lincetto, Gianluca Agresti, Mattia Rossi +1
Neural implicit modeling permits to achieve impressive 3D reconstruction results on small objects, while it exhibits significant limitations in large indoor scenes. In this work, w…