6 papers
Learning-Based Estimation of Spatially Resolved Scatter Radiation Fields in Interventional Radiology
Felix Lehner, Pasquale Lombardo, Susana Castillo +2
We present three variants of a lightweight, fully connected artificial neural network, suited for interactive estimation of three-dimensional, spatially resolved volumes of scatter…
RadField3D: A Data Generator and Data Format for Deep Learning in Radiation-Protection Dosimetry for Medical Applications
Felix Lehner, Pasquale Lombardo, Susana Castillo +2
In this research work, we present our open-source Geant4-based Monte-Carlo simulation application, called RadField3D, for generating threedimensional radiation field datasets for d…
A Bag of Tricks for Efficient Implicit Neural Point Clouds
Florian Hahlbohm, Linus Franke, Leon Overkämping +4
Implicit Neural Point Cloud (INPC) is a recent hybrid representation that combines the expressiveness of neural fields with the efficiency of point-based rendering, achieving state…
INPC: Implicit Neural Point Clouds for Radiance Field Rendering
Florian Hahlbohm, Linus Franke, Moritz Kappel +4
We introduce a new approach for reconstruction and novel view synthesis of unbounded real-world scenes. In contrast to previous methods using either volumetric fields, grid-based m…
Efficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparency
Florian Hahlbohm, Fabian Friederichs, Tim Weyrich +6
3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real-time exploration of scenes. In these applications, coherence acros…
D-NPC: Dynamic Neural Point Clouds for Non-Rigid View Synthesis from Monocular Video
Moritz Kappel, Florian Hahlbohm, Timon Scholz +5
Dynamic reconstruction and spatiotemporal novel-view synthesis of non-rigidly deforming scenes recently gained increased attention. While existing work achieves impressive quality…