Search Results for author:
Found 11 papers, 4 papers with code
Osmosis: RGBD Diffusion Prior for Underwater Image Restoration
Using this prior together with a novel guidance method based on the underwater image formation model, we generate posterior samples of clean images, removing the water effects.
Towards Monocular Shape from Refraction
In contrast, we claim that a simple energy function based on Snell's law enables the reconstruction of an arbitrary refractive surface geometry using just a single image and known background texture and geometry.
SeaThru-NeRF: Neural Radiance Fields in Scattering Media
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.
FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking Datasets
The stereo datasets include synchronized stereo images in dynamic underwater environments with objects of known-size.
Self-Supervised Monocular Depth Underwater
We suggest several additions to the self-supervised framework to cope with the underwater environment and achieve state-of-the-art results on a challenging forward-looking underwater dataset.
NAN: Noise-Aware NeRFs for Burst-Denoising
Such assumptions are not realistic in the presence of large motion and high levels of noise.
Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset
The attenuation depends both on the water body and the 3D structure of the scene, making color restoration difficult.
A Revised Underwater Image Formation Model
The current underwater image formation model descends from atmospheric dehazing equations where attenuation is a weak function of wavelength.
What Is the Space of Attenuation Coefficients in Underwater Computer Vision?
Underwater image reconstruction methods require the knowledge of wideband attenuation coefficients per color channel.
Non-Local Image Dehazing
This dependency is expressed in the transmission coefficients, that control the scene attenuation and amount of haze in every pixel.
Photometric Stereo in a Scattering Medium
Next, we model the blur due to scattering of light from the object.
