10 papers
SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splatting
Svenja Strobel, Matthias Innmann, Bernhard Egger +2
LiDAR-captured point clouds are often considered the gold standard in active 3D reconstruction. While their accuracy is exceptional in flat regions, the capturing is susceptible to…
Multi-Spectral Gaussian Splatting with Neural Color Representation
Lukas Meyer, Josef Grün, Maximilian Weiherer +3
We present MS-Splatting -- a multi-spectral 3D Gaussian Splatting (3DGS) framework that is able to generate multi-view consistent novel views from images of multiple, independent c…
MAROON: A Dataset for the Joint Characterization of Near-Field High-Resolution Radio-Frequency and Optical Depth Imaging Techniques
Vanessa Wirth, Johanna Bräunig, Nikolai Hofmann +3
Utilizing the complementary strengths of wavelength-specific range or depth sensors is crucial for robust computer-assisted tasks such as autonomous driving. Despite this, there is…
MM-2FSK: Multimodal Frequency Shift Keying for Ultra-Efficient and Robust High-Resolution MIMO Radar Imaging
Vanessa Wirth, Johanna Bräunig, Martin Vossiek +2
Accurate reconstruction of static and rapidly moving targets demands three-dimensional imaging solutions with high temporal and spatial resolution. Radar sensors are a promising se…
Refinement of Monocular Depth Maps via Multi-View Differentiable Rendering
Laura Fink, Linus Franke, Bernhard Egger +2
Accurate depth estimation is at the core of many applications in computer graphics, vision, and robotics. Current state-of-the-art monocular depth estimators, trained on extensive…
Towards Integrating Multi-Spectral Imaging with Gaussian Splatting
Josef Grün, Lukas Meyer, Maximilian Weiherer +3
We present a study of how to integrate color (RGB) and multi-spectral imagery (red, green, red-edge, and near-infrared) into the 3D Gaussian Splatting (3DGS) framework, a state-of-…