Score: 0

SWAGSplatting: Semantic-guided Water-scene Augmented Gaussian Splatting

Published: August 31, 2025 | arXiv ID: 2509.00800v1

By: Zhuodong Jiang , Haoran Wang , Guoxi Huang and more

Potential Business Impact:

Makes underwater robots see clearly in murky water.

Business Areas:
Semantic Web Internet Services

Accurate 3D reconstruction in underwater environments remains a complex challenge due to issues such as light distortion, turbidity, and limited visibility. AI-based techniques have been applied to address these issues, however, existing methods have yet to fully exploit the potential of AI, particularly in integrating language models with visual processing. In this paper, we propose a novel framework that leverages multimodal cross-knowledge to create semantic-guided 3D Gaussian Splatting for robust and high-fidelity deep-sea scene reconstruction. By embedding an extra semantic feature into each Gaussian primitive and supervised by the CLIP extracted semantic feature, our method enforces semantic and structural awareness throughout the training. The dedicated semantic consistency loss ensures alignment with high-level scene understanding. Besides, we propose a novel stage-wise training strategy, combining coarse-to-fine learning with late-stage parameter refinement, to further enhance both stability and reconstruction quality. Extensive results show that our approach consistently outperforms state-of-the-art methods on SeaThru-NeRF and Submerged3D datasets across three metrics, with an improvement of up to 3.09 dB on average in terms of PSNR, making it a strong candidate for applications in underwater exploration and marine perception.

Country of Origin
🇬🇧 United Kingdom

Page Count
5 pages

Category
Computer Science:
CV and Pattern Recognition