Interactive Example Based Terrain Generation
Events
Subscribe:  iCal  |  Google Calendar
Birmingham GB   20, Sep — 24, Sep
Chiba JP   20, Sep — 24, Sep
Ohio US   21, Sep — 24, Sep
Los Angeles US   27, Sep — 1, Oct
Latest comments
by Zac
9 hours ago

Really cool in VR, but I wish the camera would be locked to the cart, so that it felt like I was sitting in it. Now when the cart moves, the head does not follow so it feels like I'm just floating with no contact with the cart.

by edwardoamoah18@Outlook.com
10 hours ago

this is very inspirational. I love the look and feel of your environment

by TrickBox
20 hours ago

Nice ad Amazon but can we please at least have some cool behind the scene screenshot and informations instead of the regular Media tab of the official website ?

Interactive Example Based Terrain Generation
22 November, 2017
News

It appears that you can actually use deep learning to generate terrains. Don’t believe us? Eric Guérin and his team suggested a method of building complete terrain maps from a few user sketches in a paper “Interactive Example-Based Terrain Authoring with Conditional Generative Adversarial Networks“. 

Let’s start by checking out a quick overview from Two Minute Papers:

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 speci!c 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 !rst 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.

You can read the full paper here

Leave a Reply

Be the First to Comment!

avatar
wpDiscuz