Looking Into the Water by Unsupervised Learning of the Surface Shape
We address the problem of looking into the water from the air, where we seek to remove image distortions caused by refractions at the water surface. Our approach is based on modeling the different water surface structures at various points in time, assuming the underlying image is constant. To this end, we propose a model that consists of two neural-field networks. The first network predicts the height of the water surface at each spatial position and time, and the second network predicts the image color at each position. Using both networks, we reconstruct the observed sequence of images and can therefore use unsupervised training. We show that using implicit neural representations with periodic activation functions (SIREN) leads to effective modeling of the surface height spatio-temporal signal and its derivative, as required for image reconstruction. Using both simulated and real data we show that our method outperforms the latest unsupervised image restoration approach. In addition, it provides an estimate of the water surface.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ReconstructionImage RestorationSimilar Papers 제목 키워드 기반
GIFS: Neural Implicit Function for General Shape Representation
Recent development of neural implicit function has shown tremendous success on high-quality 3D shape reconstruction. However, most works divide the space into inside and outside of the shape, which limits their represent…
3D Shape ReconstructionSimultaneous 3D Reconstruction for Water Surface and Underwater Scene
This paper presents the first approach for simultaneously recovering the 3D shape of both the wavy water surface and the moving underwater scene. A portable camera array system is constructed, which captures the scene fr…
3D ReconstructionOptical Flow EstimationSurface Normals and Shape From Water
In this paper, we introduce a novel method for reconstructing surface normals and depth of dynamic objects in water. Past shape recovery methods have leveraged various visual cues for estimating shape (e.g., depth) or su…
Ghost on the Shell: An Expressive Representation of General 3D Shapes
The creation of photorealistic virtual worlds requires the accurate modeling of 3D surface geometry for a wide range of objects. For this, meshes are appealing since they 1) enable fast physics-based rendering with reali…
Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes
Neural implicit representation of geometric shapes has witnessed considerable advancements in recent years. However, common distance field based implicit representations, specifically signed distance field (SDF) for wate…