语义引导的高斯点云法用于高保真水下场景重建
Semantic-guided Gaussian Splatting for High-Fidelity Underwater Scene Reconstruction
AI总结：
本文提出SWAGSplatting框架，通过整合语义先验信息提升水下场景重建的保真度，采用语义一致性损失和自适应高斯点云重分配策略，有效解决光照不均问题，实验验证其在PSNR、SSIM和LPIPS指标上的优越性。
摘要：
在退化成像条件下实现精确的3D重建仍然是摄影测量和神经渲染中的关键挑战。在水下环境中，由于散射、衰减和稀疏观测导致的空间可见性变化，使得信息质量高度不均匀。现有3D高斯点云（3DGS）方法通常仅基于光度信号优化基本体，导致表示不平衡，在良好观测区域过拟合而在退化区域重建不足。本文提出SWAGSplatting（语义引导的水景增强高斯点云），一种多模态框架，将语义先验整合到3DGS中以实现稳健、高保真的水下重建。每个高斯基本体都附加了一个可学习的语义特征，由基于CLIP的嵌入表示监督，这些嵌入表示源自区域级提示。引入语义一致性损失以对齐几何重建与高层语义，提高结构连贯性并在挑战条件下保持显著物体边界。此外，我们提出了一种自适应的高斯基本体重分配策略，根据基本体的重要性及重建误差重新分配表示能力，缓解传统密集化引入的不平衡。这使得在不增加计算成本的情况下，更有效地建模低可见性区域。在真实世界数据集SeaThru-NeRF、Submerged3D和S-UW上进行了大量实验，结果表明，所提出的方法在平均PSNR、SSIM和LPIPS指标上均优于最先进的方法。结果验证了整合语义先验信息在高保真水下场景重建中的有效性。代码可在https://github.com/theflash987/SWAGSplatting获取。
英文摘要：
Accurate 3D reconstruction in degraded imaging conditions remains a key challenge in photogrammetry and neural rendering. In underwater environments, spatially varying visibility caused by scattering, attenuation, and sparse observations leads to highly non-uniform information quality. Existing 3D Gaussian Splatting (3DGS) methods typically optimize primitives based on photometric signals alone, resulting in imbalanced representation, with overfitting in well-observed regions and insufficient reconstruction in degraded areas. In this paper, we propose SWAGSplatting (Semantic-guided Water-scene Augmented Gaussian Splatting), a multimodal framework that integrates semantic priors into 3DGS for robust, high-fidelity underwater reconstruction. Each Gaussian primitive is augmented with a learnable semantic feature, supervised by CLIP-based embeddings derived from region-level cues. A semantic consistency loss is introduced to align geometric reconstruction with high-level semantics, improving structural coherence and preserving salient object boundaries under challenging conditions. Furthermore, we propose an adaptive Gaussian primitive reallocation strategy that redistributes representation capacity based on both primitive importance and reconstruction error, mitigating the imbalance introduced by conventional densification. This enables more effective modeling of low-visibility regions without increasing computational cost. Extensive experiments on real-world datasets, including SeaThru-NeRF, Submerged3D, and S-UW, demonstrate that the proposed method consistently outperforms state-of-the-art approaches in terms of average PSNR, SSIM, and LPIPS. The results validate the effectiveness of integrating semantic priors for high-fidelity underwater scene reconstruction. Code is available at https://github.com/theflash987/SWAGSplatting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
