arXiv 2603.216952026-08-28cs.CVcs.GR

RefracGS：通过折射水表面进行新颖视图合成

RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing

Shandong University, China（山东大学）；Peking University, Beijing, China（北京大学）；Sun Yat-sen University, China（中山大学）；Beijing Academy of Artificial Intelligence, Beijing, China（北京人工智能研究院）

Yiming Shao, Qiyu Dai, Chong Gao, Guanbin Li, Yequan Wang, He Sun, Qiong Zeng, Baoquan Chen, Wenzheng Chen

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

RefracGS通过3D高斯射线追踪方法，结合折射水面与底层场景的重建，实现高保真新颖视图合成，实验表明其在视觉质量和效率上优于现有方法。

摘要：

新颖视图合成（NVS）通过非平面折射表面面临严重挑战，因为存在剧烈的空间变化光学畸变。尽管最近的表示方法如NeRF和3D高斯点撒（3DGS）在NVS方面表现优异，但其对直线射线传播的假设在这些条件下失效，导致显著的伪影。为克服这一限制，我们引入了RefracGS框架，该框架联合重建折射水表面和界面下的场景。我们的关键见解是显式地将折射边界与目标物体分离：折射表面通过神经高度场建模，捕捉波形几何，而底层场景则表示为3D高斯场。我们提出了一个折射感知的高斯射线追踪方法，利用斯涅尔定律准确计算非线性射线轨迹，并高效渲染底层高斯场，同时将损失梯度反向传播到参数化的折射表面。通过端到端联合优化两种表示，我们的方法确保了高保真的NVS和视图一致的表面恢复。在合成和现实场景中的复杂波实验表明，RefracGS在视觉质量和效率上优于现有折射方法，同时实现了15倍更快的训练和实时渲染（200 FPS）。RefracGS的项目页面可在https://yimgshao.github.io/refracgs/上找到。

英文摘要：

Novel view synthesis (NVS) through non-planar refractive surfaces presents fundamental challenges due to severe, spatially varying optical distortions. While recent representations like NeRF and 3D Gaussian Splatting (3DGS) excel at NVS, their assumption of straight-line ray propagation fails under these conditions, leading to significant artifacts. To overcome this limitation, we introduce RefracGS, a framework that jointly reconstructs the refractive water surface and the scene beneath the interface. Our key insight is to explicitly decouple the refractive boundary from the target objects: the refractive surface is modeled via a neural height field, capturing wave geometry, while the underlying scene is represented as a 3D Gaussian field. We formulate a refraction-aware Gaussian ray tracing approach that accurately computes non-linear ray trajectories using Snell's law and efficiently renders the underlying Gaussian field while backpropagating the loss gradients to the parameterized refractive surface. Through end-to-end joint optimization of both representations, our method ensures high-fidelity NVS and view-consistent surface recovery. Experiments on both synthetic and real-world scenes with complex waves demonstrate that RefracGS outperforms prior refractive methods in visual quality, while achieving 15x faster training and real-time rendering at 200 FPS. The project page for RefracGS is available at https://yimgshao.github.io/refracgs/.

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。