Presentation

<
CaRaFe: Camera-Radar Radiance Fields for Scene Reconstruction
SessionReconstruction
DescriptionCaRaFe is the first method to jointly reconstruct 3D scenes from both camera and radar data using a multi-modal shared neural geometry representation. It can reconstruct large-scale urban environments from a single drive-through and synthesize measurements from both sensors at novel viewpoints, leveraging their complementary strengths to improve geometric fidelity.
Authors
David Borts
ETH Zürich
Julian Ost
Princeton University
Torc Robotics
Shamik Basu
INRIA
Tim Broedermann
ETH Zürich
Andrea Ramazzina
Mercedes-Benz
Technical University of Munich
Christos Sakaridis
ETH Zürich
Mario Bijelic
Princeton University
Torc Robotics
Felix Heide
Princeton University
Torc Robotics
Event Type
Technical Paper
TimeWednesday, 22 July 202611:05am - 11:15am PDT
LocationRoom 408 B
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Wednesday, 22 July 202610:45am - 12:35pm PDTRoom 408 B
Keywords
Artificial Intelligence/Machine Learning
Geometry
Modeling
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationPixels2Peaks: Converting Terrain Images to Heightmaps
Similar Presentations
A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction
Learning View-Dependent Splatting Kernels
ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation