loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Marcel Rogge 1 ; 2 and Didier Stricker 1 ; 2

Affiliations: 1 Augmented Vision, University of Kaiserslautern-Landau, Kaiserslautern, Germany ; 2 Department of Augmented Vision, Deutsches Forschungszentrum fuer Kuenstliche Intelligenz, Kaiserslautern, Germany

Keyword(s): Novel View Synthesis, Radiance Fields, Gaussian Splatting, Surface Reconstruction.

Abstract: Current Gaussian Splatting approaches are effective for reconstructing entire scenes but lack the option to target specific objects, making them computationally expensive and unsuitable for object-specific applications. We propose a novel approach that leverages object masks to enable targeted reconstruction, resulting in object-centric models. Additionally, we introduce an occlusion-aware pruning strategy to minimize the number of Gaussians without compromising quality. Our method reconstructs compact object models, yielding object-centric Gaussian and mesh representations that are up to 96% smaller and up to 71% faster to train compared to the baseline while retaining competitive quality. These representations are immediately usable for downstream applications such as appearance editing and physics simulation without additional processing.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.15.223.214

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Rogge, M. and Stricker, D. (2025). Object-Centric 2D Gaussian Splatting: Background Removal and Occlusion-Aware Pruning for Compact Object Models. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-758-730-6; ISSN 2184-4313, SciTePress, pages 519-530. DOI: 10.5220/0013305500003905

@conference{icpram25,
author={Marcel Rogge and Didier Stricker},
title={Object-Centric 2D Gaussian Splatting: Background Removal and Occlusion-Aware Pruning for Compact Object Models},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2025},
pages={519-530},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013305500003905},
isbn={978-989-758-730-6},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - Object-Centric 2D Gaussian Splatting: Background Removal and Occlusion-Aware Pruning for Compact Object Models
SN - 978-989-758-730-6
IS - 2184-4313
AU - Rogge, M.
AU - Stricker, D.
PY - 2025
SP - 519
EP - 530
DO - 10.5220/0013305500003905
PB - SciTePress