EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Stereo-GS: Online 3D Gaussian Splatting Mapping Using Stereo Depth Estimation

Junkyu Park, Byeonggwon Lee, Sanggi Lee, Soohwan Song

Electronics · 14.11.2025 · 14 (22) · 4436

DOI: 10.3390/electronics14224436 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 14.11.2025. Verfasst von Junkyu Park und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute of Energy Technology Evaluation and Planning, Ministry of Trade, Industry and Energy (MOTIE), Korea, Institute of Information & Communication Technology Planning & Evaluation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present Stereo-GS, a real-time system for online 3D Gaussian Splatting (3DGS) that reconstructs photorealistic 3D scenes from streaming stereo pairs. Unlike prior offline 3DGS methods that require dense multi-view input or precomputed depth, Stereo-GS estimates metrically accurate depth maps directly from rectified stereo geometry, enabling progressive, globally consistent reconstruction. The frontend combines a stereo implementation of DROID-SLAM for robust tracking and keyframe selection with FoundationStereo, a generalizable stereo network that needs no scene-specific fine-tuning. A two-stage filtering pipeline improves depth reliability by removing outliers using a variance-based refinement filter followed by a multi-view consistency check. In the backend, we selectively initialize new Gaussians in under-represented regions flagged by low PSNR during rendering and continuously optimize them via differentiable rendering. To maintain global coherence with minimal overhead, we apply a lightweight rigid alignment after periodic bundle adjustment. On EuRoC and TartanAir, Stereo-GS attains state-of-the-art performance, improving average PSNR by 0.22 dB and 2.45 dB over the best baseline, respectively. Together with superior visual quality, these results show that Stereo-GS delivers high-fidelity, geometrically accurate 3D reconstructions suitable for real-time robotics, navigation, and immersive AR/VR applications.

Förderung

  • Korea Institute of Energy Technology Evaluation and Planning
  • Ministry of Trade, Industry and Energy (MOTIE), Korea
  • Institute of Information & Communication Technology Planning & Evaluation

Zitieren

APA

Park, J., Lee, B., Lee, S., & Song, S. (2025). Stereo-GS: Online 3D Gaussian Splatting Mapping Using Stereo Depth Estimation. Electronics, 14(22), 4436. https://doi.org/10.3390/electronics14224436

Vancouver

Park J, Lee B, Lee S, Song S. Stereo-GS: Online 3D Gaussian Splatting Mapping Using Stereo Depth Estimation. Electronics. 2025;14(22):4436. doi:10.3390/electronics14224436

BibTeX
@article{Park2025,
  author = {Park, Junkyu and Lee, Byeonggwon and Lee, Sanggi and Song, Soohwan},
  title = {Stereo-GS: Online 3D Gaussian Splatting Mapping Using Stereo Depth Estimation},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {22},
  pages = {4436},
  doi = {10.3390/electronics14224436}
}
Kostenlos starten →