Interactive Example-Based Terrain Authoring with Conditional Generative Adversarial Networks

Eric Guérin; Julie Digne; Eric Galin; Adrien Peytavie; Christian Wolf; Bedrich Benes; Benoît Martinez

Interactive Example-Based Terrain Authoring with Conditional Generative Adversarial Networks

Eric Guérin ¹ Julie Digne ¹ Eric Galin ¹ Adrien Peytavie ¹ Christian Wolf ² Bedrich Benes ³ Benoît Martinez ⁴

1 GeoMod - Modélisation Géométrique, Géométrie Algorithmique, Fractales

LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information

2 imagine - Extraction de Caractéristiques et Identification

LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information

3 Department of Computer Science [Purdue]

4 Ubisoft

Abstract : Authoring virtual terrains presents a challenge and there is a strong need for authoring tools able to create realistic terrains with simple user-inputs and with high user control. We propose an example-based authoring pipeline that uses a set of terrain synthesizers dedicated to specific tasks. Each terrain synthesizer is a Conditional Generative Adversarial Network trained by using real-world terrains and their sketched counterparts. The training sets are built automatically with a view that the terrain synthesizers learn the generation from features that are easy to sketch. During the authoring process, the artist first creates a rough sketch of the main terrain features, such as rivers, valleys and ridges, and the algorithm automatically synthesizes a terrain corresponding to the sketch using the learned features of the training samples. Moreover, an erosion synthesizer can also generate terrain evolution by erosion at a very low computational cost. Our framework allows for an easy terrain authoring and provides a high level of realism for a minimum sketch cost. We show various examples of terrain synthesis created by experienced as well as inexperienced users who are able to design a vast variety of complex terrains in a very short time.

Keywords : procedural modeling deep learning terrain generation

Document type :

Journal articles

Domain :

Computer Science [cs] / Graphics [cs.GR]

Complete list of metadatas

Cited literature [56 references] Display Hide Download

https://hal.archives-ouvertes.fr/hal-01583706
Contributor : Christian Wolf <>
Submitted on : Thursday, September 28, 2017 - 12:32:08 PM
Last modification on : Monday, February 25, 2019 - 4:48:59 PM

tog.pdf

Files produced by the author(s)

Interactive Example-Based Terrain Authoring with Conditional Generative Adversarial Networks

File

Identifiers

Collections

Citation

Export

Metrics

1654

26108

Contact

Interactive Example-Based Terrain Authoring with Conditional Generative Adversarial Networks

File

Identifiers

Collections

Citation

Export

Share

Metrics

1654

26108

Contact