AquaFuse: Waterbody Fusion for Physics Guided View Synthesis of Underwater Scenes
Not on the map. Why?
Abstract (arXiv)
We introduce the idea of AquaFuse, a physics-based method for synthesizing waterbody properties in underwater imagery. We formulate a closed-form solution for waterbody fusion that facilitates realistic data augmentation and geometrically consistent underwater scene rendering. AquaFuse leverages the physical characteristics of light propagation underwater to synthesize the waterbody from one scene to the object contents of another. Unlike data-driven style transfer, AquaFuse preserves the depth consistency and object geometry in an input scene. We validate this unique feature by comprehensive experiments over diverse underwater scenes. We find that the AquaFused images preserve over 94% depth consistency and 90-95% structural similarity of the input scenes. We also demonstrate that it generates accurate 3D view synthesis by preserving object geometry while adapting to the inherent waterbody fusion process. AquaFuse opens up a new research direction in data augmentation by geometry-preserving style transfer for underwater imaging and robot vision applications.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 19 of its 50 references that are in the map. First posted on arXiv 2 Nov 2024.
Builds on
19 of 50 references.
References · 19
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
- 2019An Underwater Image Enhancement Benchmark Dataset and Beyondcited by 250
- 2021StyTr2: Image Style Transfer with Transformerscited by 186
- 2019Fast Underwater Image Enhancement for Improved Visual Perceptioncited by 181
- 2017WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Imagescited by 112
- 2018Enhancing Underwater Imagery using Generative Adversarial Networkscited by 94
- 2020Arbitrary Video Style Transfer via Multi-Channel Correlationcited by 84
- 2023SeaThru-NeRF: Neural Radiance Fields in Scattering Mediacited by 75
- 2020Arbitrary Style Transfer via Multi-Adaptation Networkcited by 70
- 2020Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perceptioncited by 53
- 2022UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scenecited by 47
7 more
- 2017Emerging from Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfercited by 40
- 2024WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splattingcited by 39
- 2024SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Modelcited by 35
- 2021PhotoWCT2: Compact Autoencoder for Photorealistic Style Transfer Resulting from Blockwise Training and Skip Connections of High-Frequency Residualscited by 30
- 2022UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robotscited by 27
- 2024RecGS: Removing Water Caustic with Recurrent Gaussian Splattingcited by 15
- 2023CaveSeg: Deep Semantic Segmentation and Scene Parsing for Autonomous Underwater Cave Explorationcited by 7
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.