Underwater360: Reconstructing Underwater Scenes from Panoramic Images with Omnidirectional Gaussian Splatting
Not on the map. Why?
Abstract (arXiv)
Underwater scene reconstruction is essential for immersive exploration of aquatic environments, yet remains challenging due to complex participating-media effects such as absorption and scattering, as well as the limited field of view (FoV) of conventional cameras. Although combining panoramic imaging with 3D Gaussian Splatting (3DGS) offers a promising direction for photorealistic underwater rendering, traditional 3DGS struggles with both spherical projection distortion and underwater medium degradation. In this paper, we propose Underwater360, a physics-informed omnidirectional 3DGS framework for underwater panoramic scene reconstruction. First, we introduce an Omnidirectional Gaussian Splatting module that performs ray casting directly in spherical camera space instead of relying on 2D projection approximations, thereby reducing geometric distortions under 360^circ FoV. Second, we design a physics-based appearance-medium modeling architecture with pose-conditioned appearance embeddings to explicitly decouple intrinsic scene radiance from depth-dependent backscatter and attenuation, enabling physically grounded scene appearance restoration. Finally, we establish a new panoramic underwater benchmark dataset containing both synthetic and real-world scenes. Extensive experiments demonstrate that Underwater360 achieves superior performance in underwater novel view synthesis and scene appearance restoration, delivering improved rendering quality and cross-view consistency in complex underwater environments. The code and datasets are released at https://github.com/SwcK423/Underwater360
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 27 references that are in the map. First posted on arXiv 26 May 2026.
Builds on
18 of 27 references.
References · 18
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
- 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
- 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
- 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
- 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
- 2023SeaThru-NeRF: Neural Radiance Fields in Scattering Mediacited by 75
- 2024WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splattingcited by 39
- 2024360-GS: Layout-guided Panoramic Gaussian Splatting For Indoor Roamingcited by 35
- 2024SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Modelcited by 35
- 2023Balanced Spherical Grid for Egocentric View Synthesiscited by 29
6 more
- 2024UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstructioncited by 23
- 2024OmniGS: Fast Radiance Field Reconstruction using Omnidirectional Gaussian Splattingcited by 20
- 2024ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattingscited by 19
- 2024Aquatic-GS: A Hybrid 3D Representation for Underwater Scenescited by 8
- 2024Gaussian Splashing: Direct Volumetric Rendering Underwatercited by 7
- 20253D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decouplingcited by 5
Built on by
Not cited yet.