Interactive Example-Based Terrain Authoring with Conditional Generative Adversarial Networks

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

ACM Transactions on Graphics, Vol. 36, No. 6, Article 228, November 2017. Siggraph Asia 2017 Proceedings, Bangkok, Thailand.

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.



@article {guerin2017,
  author = {Guérin, Eric and Digne, Julie and Galin, 
            Eric and Peytavie, Adrien and Wolf, Christian
            and Benes, Bedrich and Martinez, Benoit},
  title = {Interactive Example-Based Terrain Authoring 
           with Conditional Generative Adversarial Networks},
  journal = {ACM Transactions on Graphics 
             (proceedings of Siggraph Asia 2017)},
  volume = {36},
  number = {6},
  year = {2017},

2 réponses à “Interactive Example-Based Terrain Authoring with Conditional Generative Adversarial Networks

  1. Ping : Dark Matter: 19 September 2017 | Ian Fitzpatrick

  2. Ping : Terrain Generation with Deep Learning