TemPCC: Completing Temporal Occlusions in Large Dynamic Point Clouds captured by Multiple RGB-D Cameras
Loading...
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
We present TemPCC, an approach to complete temporal occlusions in large dynamic point clouds. Our method manages a point set over time, integrates new observations into this set, and predicts the motion of occluded points based on the flow of surrounding visible ones. Unlike existing methods, our approach efficiently handles arbitrarily large point sets with linear complexity, does not reconstruct a canonical representation, and considers only local features. Our tests, performed on an Nvidia GeForce RTX 4090, demonstrate that our approach can complete a frame with 30,000 points in under 30 ms, while, in general, being able to handle point sets exceeding 1,000,000 points. This scalability enables the mitigation of temporal occlusions across entire scenes captured by multi-RGB-D camera setups. Our initial results demonstrate that self-occlusions are effectively completed and successfully generalized to unknown scenes despite limited training data.
Description
CCS Concepts: Computing methodologies → Point-based models; Information systems → Spatial-temporal systems
@inproceedings{10.2312:egs.20251039,
booktitle = {Eurographics 2025 - Short Papers},
editor = {Ceylan, Duygu and Li, Tzu-Mao},
title = {{TemPCC: Completing Temporal Occlusions in Large Dynamic Point Clouds captured by Multiple RGB-D Cameras}},
author = {Mühlenbrock, Andre and Weller, Rene and Zachmann, Gabriel},
year = {2025},
publisher = {The Eurographics Association},
ISSN = {1017-4656},
ISBN = {978-3-03868-268-4},
DOI = {10.2312/egs.20251039}
}