RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917357886111744 |
|---|---|
| author | Shao, Yiming Dai, Qiyu Gao, Chong Li, Guanbin Wang, Yeqiang Sun, He Zeng, Qiong Chen, Baoquan Chen, Wenzheng |
| author_facet | Shao, Yiming Dai, Qiyu Gao, Chong Li, Guanbin Wang, Yeqiang Sun, He Zeng, Qiong Chen, Baoquan Chen, Wenzheng |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21695 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing Shao, Yiming Dai, Qiyu Gao, Chong Li, Guanbin Wang, Yeqiang Sun, He Zeng, Qiong Chen, Baoquan Chen, Wenzheng Computer Vision and Pattern Recognition Graphics 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/. |
| title | RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2603.21695 |