Water Simulation and Rendering from a Still Photograph

TL;DR

This paper introduces a novel method to generate realistic, animated water surfaces from a single photograph, combining neural networks and traditional techniques for real-time rendering and editing.

Contribution

It presents a new approach that estimates water surface parameters and reflections from a single image, enabling realistic animation and interaction without user intervention.

Findings

Produces realistic water animations from a single photo

Supports real-time rendering and editing of water surfaces

Works across diverse natural scenes with different lighting conditions

Abstract

We propose an approach to simulate and render realistic water animation from a single still input photograph. We first segment the water surface, estimate rendering parameters, and compute water reflection textures with a combination of neural networks and traditional optimization techniques. Then we propose an image-based screen space local reflection model to render the water surface overlaid on the input image and generate real-time water animation. Our approach creates realistic results with no user intervention for a wide variety of natural scenes containing large bodies of water with different lighting and water surface conditions. Since our method provides a 3D representation of the water surface, it naturally enables direct editing of water parameters and also supports interactive applications like adding synthetic objects to the scene.