.png){kind=icon}
.png){kind=icon}
Return
Multi-Theme Generative Adversarial Terrain Amplification
.png){kind=icon}
OA
AI
DOI：10.1145/3355089.3356553.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Achieving highly detailed terrain models spanning vast areas is crucial to modern computer graphics. The pipeline for obtaining such terrains is via amplification of a low-resolution terrain to refine the details given a desired theme, which is a time-consuming and labor-intensive process. Recently, data-driven methods, such as the sparse construction tree, have provided a promising direction to equip the artist with better control over the theme. These methods learn to amplify terrain details by using an exemplar of high-resolution detailed terrains to transfer the theme. In this paper, we propose Generative Adversarial Terrain Amplification (GATA) that achieves better local/global coherence compared 10 the existing data-driven methods while providing even more ways to control the theme. GATA is comprised of two key ingredients. The first one is a novel embedding of themes into vectors of real numbers to achieve a single tool for multi-theme amplification. The theme component can leverage existing LTIDAR data to generate similar terrain features. It can also generate new fictional themes by tuning the embedding vector or even encoding a new example terrain into an embedding. The second one is an adversarially trained model that, conditioned on an embedding and a low-resolution terrain, generates a high-resolution terrain adhering to the desired theme. The proposed integral approach reduces the need for unnecessary manual adjustments, can speed up the development, and brings the model quality to a new level. Our implementation of the proposed method has proved successful in large-scale terrain authoring for an open-world game.
Keywords:
terrain amplification
generative models
generative adversarial networks (GANs)
style transfer
embedding
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.5
Papers:
4.7K
Citations:
3.6W
Organization
No organization information available