Looking Into the Water by Unsupervised Learning of the Surface Shape

• URL: http://arxiv.org/abs/2603.07614v1
• Date: Sun, 08 Mar 2026 12:54:41 GMT
• Title: Looking Into the Water by Unsupervised Learning of the Surface Shape
• Abstract summary: 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.<n>Our approach is based on modeling the different water surface structures at various points in time, assuming the underlying image is constant.
• Score: 5.875225219574616
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Geometric Flood Depth Estimation: Fusing Transformer-Based Segmentation with Digital Elevation Models [0.0]
  Post-disaster situational awareness relies heavily on understanding both the extent and the volume of floodwaters.<n>This paper presents a geometric "Water Surface Elevation" approach for estimating flood depth from monocular aerial imagery.<n>Our pipeline utilizes Mask2Former, a state-of-the-art transformer-based segmentation model, to generate precise 2D flood masks.
  arXiv  Detail & Related papers  (2026-05-08T22:05:17Z)
• NeuroPump: Simultaneous Geometric and Color Rectification for Underwater Images [52.863935209616635]
  Underwater image restoration aims to remove geometric and color distortions due to water refraction, absorption and scattering.<n>We propose NeuroPump, a self-supervised method to simultaneously optimize and rectify underwater geometry and color as if water were pumped out.
  arXiv  Detail & Related papers  (2024-12-20T13:40:28Z)
• Physics Informed and Data Driven Simulation of Underwater Images via Residual Learning [5.095097384893417]
  In general, underwater images suffer from color distortion and low contrast, because light is attenuated and backscattered as it propagates through water. An existing simple degradation model (similar to atmospheric image "hazing" effects) is not sufficient to properly represent the underwater image degradation. We propose a deep learning-based architecture to automatically simulate the underwater effects.
  arXiv  Detail & Related papers  (2024-02-07T21:53:28Z)
• Ghost on the Shell: An Expressive Representation of General 3D Shapes [97.76840585617907]
  Meshes are appealing since they enable fast physics-based rendering with realistic material and lighting. Recent work on reconstructing and statistically modeling 3D shapes has critiqued meshes as being topologically inflexible. We parameterize open surfaces by defining a manifold signed distance field on watertight surfaces. G-Shell achieves state-of-the-art performance on non-watertight mesh reconstruction and generation tasks.
  arXiv  Detail & Related papers  (2023-10-23T17:59:52Z)
• PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators [120.06891448820447]
  How to obtain clear and visually pleasant images has become a common concern of people. The task of underwater image enhancement (UIE) has also emerged as the times require. In this paper, we propose a physical model-guided GAN model for UIE, referred to as PUGAN. Our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics.
  arXiv  Detail & Related papers  (2023-06-15T07:41:12Z)
• DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge Distillation [44.99833362998488]
  We present DeepAqua, a self-supervised deep learning model that eliminates the need for manual annotations during the training phase. We exploit cases where optical- and radar-based water masks coincide, enabling the detection of both open and vegetated water surfaces. Experimental results show that DeepAqua outperforms other unsupervised methods by improving accuracy by 7%, Intersection Over Union by 27%, and F1 score by 14%.
  arXiv  Detail & Related papers  (2023-05-02T18:06:21Z)
• Unpaired Overwater Image Defogging Using Prior Map Guided CycleGAN [60.257791714663725]
  We propose a Prior map Guided CycleGAN (PG-CycleGAN) for defogging of images with overwater scenes. The proposed method outperforms the state-of-the-art supervised, semi-supervised, and unsupervised defogging approaches.
  arXiv  Detail & Related papers  (2022-12-23T03:00:28Z)
• Seafloor-Invariant Caustics Removal from Underwater Imagery [0.0]
  Caustics are complex physical phenomena resulting from the projection of light rays being refracted by the wavy surface. In this work, we propose a novel method for correcting the effects of caustics on shallow underwater imagery. In particular, the developed method employs deep learning architectures in order to classify image pixels to "non-caustics" and "caustics"
  arXiv  Detail & Related papers  (2022-12-20T11:11:02Z)
• Water Simulation and Rendering from a Still Photograph [20.631819299595527]
  We propose an approach to simulate and render realistic water animation from a single still input photograph. Our approach creates realistic results with no user intervention for a wide variety of natural scenes.
  arXiv  Detail & Related papers  (2022-10-05T20:47:44Z)
• Z2P: Instant Rendering of Point Clouds [104.1186026323896]
  We present a technique for rendering point clouds using a neural network. Existing point rendering techniques either use splatting, or first reconstruct a surface mesh that can then be rendered.
  arXiv  Detail & Related papers  (2021-05-30T13:58:24Z)
• Learning to Restore a Single Face Image Degraded by Atmospheric Turbulence using CNNs [93.72048616001064]
  Images captured under such condition suffer from a combination of geometric deformation and space varying blur. We present a deep learning-based solution to the problem of restoring a turbulence-degraded face image.
  arXiv  Detail & Related papers  (2020-07-16T15:25:08Z)
• Breaking the Limits of Remote Sensing by Simulation and Deep Learning for Flood and Debris Flow Mapping [13.167695669500391]
  We propose a framework that estimates inundation depth and debris-flow-induced topographic deformation from remote sensing imagery. A water and debris flow simulator generates training data for various artificial disaster scenarios. We show that regression models based on Attention U-Net and LinkNet architectures trained on such synthetic data can predict the maximum water level and topographic deformation.
  arXiv  Detail & Related papers  (2020-06-09T10:59:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.