CRISTAL: Real-time Camera Registration in Static LiDAR Scans using Neural Rendering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vanherck, Joni, Moonen, Steven, Zoomers, Brent, Werner, Kobe, Put, Jeroen, Jorissen, Lode, Michiels, Nick
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911321647218688
author Vanherck, Joni
Moonen, Steven
Zoomers, Brent
Werner, Kobe
Put, Jeroen
Jorissen, Lode
Michiels, Nick
author_facet Vanherck, Joni
Moonen, Steven
Zoomers, Brent
Werner, Kobe
Put, Jeroen
Jorissen, Lode
Michiels, Nick
contents Accurate camera localization is crucial for robotics and Extended Reality (XR), enabling reliable navigation and alignment of virtual and real content. Existing visual methods often suffer from drift, scale ambiguity, and depend on fiducials or loop closure. This work introduces a real-time method for localizing a camera within a pre-captured, highly accurate colored LiDAR point cloud. By rendering synthetic views from this cloud, 2D-3D correspondences are established between live frames and the point cloud. A neural rendering technique narrows the domain gap between synthetic and real images, reducing occlusion and background artifacts to improve feature matching. The result is drift-free camera tracking with correct metric scale in the global LiDAR coordinate system. Two real-time variants are presented: Online Render and Match, and Prebuild and Localize. We demonstrate improved results on the ScanNet++ dataset and outperform existing SLAM pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16349
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CRISTAL: Real-time Camera Registration in Static LiDAR Scans using Neural Rendering
Vanherck, Joni
Moonen, Steven
Zoomers, Brent
Werner, Kobe
Put, Jeroen
Jorissen, Lode
Michiels, Nick
Computer Vision and Pattern Recognition
Graphics
Accurate camera localization is crucial for robotics and Extended Reality (XR), enabling reliable navigation and alignment of virtual and real content. Existing visual methods often suffer from drift, scale ambiguity, and depend on fiducials or loop closure. This work introduces a real-time method for localizing a camera within a pre-captured, highly accurate colored LiDAR point cloud. By rendering synthetic views from this cloud, 2D-3D correspondences are established between live frames and the point cloud. A neural rendering technique narrows the domain gap between synthetic and real images, reducing occlusion and background artifacts to improve feature matching. The result is drift-free camera tracking with correct metric scale in the global LiDAR coordinate system. Two real-time variants are presented: Online Render and Match, and Prebuild and Localize. We demonstrate improved results on the ScanNet++ dataset and outperform existing SLAM pipelines.
title CRISTAL: Real-time Camera Registration in Static LiDAR Scans using Neural Rendering
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2511.16349