Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

SeaThru-NeRF: Neural Radiance Fields in Scattering Media

About

Research on neural radiance fields (NeRFs) for novel view generation is exploding with new models and extensions. However, a question that remains unanswered is what happens in underwater or foggy scenes where the medium strongly influences the appearance of objects. Thus far, NeRF and its variants have ignored these cases. However, since the NeRF framework is based on volumetric rendering, it has inherent capability to account for the medium's effects, once modeled appropriately. We develop a new rendering model for NeRFs in scattering media, which is based on the SeaThru image formation model, and suggest a suitable architecture for learning both scene information and medium parameters. We demonstrate the strength of our method using simulated and real-world scenes, correctly rendering novel photorealistic views underwater. Even more excitingly, we can render clear views of these scenes, removing the medium between the camera and the scene and reconstructing the appearance and depth of far objects, which are severely occluded by the medium. Our code and unique datasets are available on the project's website.

Deborah Levy, Amit Peleg, Naama Pearl, Dan Rosenbaum, Derya Akkaynak, Simon Korman, Tali Treibitz• 2023

Related benchmarks

TaskDatasetResultRank
Novel View SynthesisSeaThru-NeRF Panama
PSNR30.6
11
Novel View SynthesisSeaThru-NeRF (IUI3-RedSea)
PSNR29
11
Novel View SynthesisSeaThru-NeRF Curasao
PSNR30.86
11
Novel View SynthesisSeaThru-NeRF (J.G.-RedSea)
PSNR23.11
11
Novel View SynthesisCoral In-the-Wild
PSNR27.6
6
Novel View SynthesisIn-the-Wild Composite
PSNR24.15
6
Novel View SynthesisUnderwater Scenes
Training Time321
6
Novel View SynthesisSeaThru D3 (test)
PSNR20.34
5
Novel View SynthesisSeaThru D5 (test)
PSNR24.34
5
Novel View SynthesisShipWreck 1 (test)
PSNR20
5
Showing 10 of 25 rows

Other info

Code

Follow for update