水下
声纳
渲染(计算机图形)
稳健性(进化)
计算机科学
可视外壳
杠杆(统计)
计算机视觉
人工智能
三维重建
单眼
计算机图形学(图像)
高斯分布
基于图像的建模与绘制
体绘制
变形
图形管道
迭代重建
实体造型
单摄像机
图像形成
作者
Zijie Ling,Yunxuan Feng,Meng Ao,Renxiang Xiao,Shu Pan,Wenjie Lu,Liang Hu
标识
DOI:10.1109/lra.2025.3615528
摘要
Differentiable Gaussian Splatting (GS) has emerged as a powerful paradigm for scene representation, enabling efficient rendering and real-time editing. However, existing GS-based methods, which rely mainly on clear visual images, perform poorly in underwater environments due to camera distortions such as light absorption and backscattering. In contrast, acoustic sensors like Forward Looking Sonar (FLS) offer superior penetration and robustness in such conditions. To leverage the complementary merits of visual and FLS images, we propose a novel GS framework customized for underwater scenarios, termed Aqua-Splat, for robust and accurate underwater perception. It ensures physically consistent reconstruction by incorporating the sonar wave propagation modeling in the image formation process. Moreover, we propose a volume rendering technique for sonar image synthesis, achieving similar speed to visual rendering. Additionally, we introduce a sonar-guided densification strategy to optimize the scene representation. Through extensive experiments on both simulated and datasets from the lab pool, we demonstrate that Aqua-Splat significantly improves image synthesis and 3D scene reconstruction in challenging underwater environments, outperforming existing methods in terms of both geometric accuracy and photometric fidelity. The code of Aqua-Splat will be open-sourced later for the community.
科研通智能强力驱动
Strongly Powered by AbleSci AI