Water Simulation and Rendering from a Still Photograph
This enables automatic water animation from photos for applications like visual effects and interactive editing, though it appears incremental as it combines neural networks with traditional techniques.
The paper tackles the problem of generating realistic water animation from a single still photograph by segmenting the water surface, estimating rendering parameters, and using an image-based reflection model to create real-time animation. The approach produces realistic results automatically for various natural scenes with large bodies of water under different conditions.
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.