DiGS: Depth-Initialized Gaussian Splatting for Single-Object Reconstruction
Journal of Imaging · 24.04.2026 · 12 (5) · 183
DOI: 10.3390/jimaging12050183 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 24.04.2026. Verfasst von Jacopo Meglioraldi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of the Arts, University of Bologna, Via Barberia 4, 40123 Bologna, Italy. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Gaussian Splatting is a state-of-the-art technique for 3D reconstruction. In this paper, we investigate how different initialization strategies influence the optimization process within the Gaussian Splatting framework, showing that more accurate initial point clouds can greatly influence the quality of object reconstruction. We introduce the Depth-initialized Gaussian Splatting (DiGS) approach, a pipeline that leverages depth-based initialization. By incorporating depth data from a calibrated stereo camera setup, the proposed method significantly enhances model performance, particularly during the early optimization stages. DiGS is particularly effective for reconstructing isolated single objects and improving the recovery of fine-grained details. Several tests on synthetic and real-world datasets confirm the effectiveness of the proposed pipeline. To evaluate our approach, we employ objective metrics and a user study involving 20 participants to assess with human perception the quality of the proposed approach.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of the Arts, University of Bologna, Via Barberia 4, 40123 Bologna, Italy.
ORCID-Profile: Jacopo Meglioraldi, Pasquale Cascarano, Gustavo Marfia
Zitieren
APA
Meglioraldi, J., Cascarano, P., & Marfia, G. (2026). DiGS: Depth-Initialized Gaussian Splatting for Single-Object Reconstruction. Journal of Imaging, 12(5), 183. https://doi.org/10.3390/jimaging12050183
Vancouver
Meglioraldi J, Cascarano P, Marfia G. DiGS: Depth-Initialized Gaussian Splatting for Single-Object Reconstruction. Journal of Imaging. 2026;12(5):183. doi:10.3390/jimaging12050183
BibTeX
@article{Meglioraldi2026,
author = {Meglioraldi, Jacopo and Cascarano, Pasquale and Marfia, Gustavo},
title = {DiGS: Depth-Initialized Gaussian Splatting for Single-Object Reconstruction},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {5},
pages = {183},
doi = {10.3390/jimaging12050183}
}
EUVIMED