Interactive example-based terrain authoring with conditional generative adversarial networks

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 specic 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.

Sketch2VF: Sketch‐based flow design with conditional generative adversarial network

“…Data‐Driven Approaches: Deep learning–based approaches stochastically generate complex natural images such as human faces from a distribution represented by a given training set and 3D terrain fields . However, in general, the input data are abstracted into high‐dimensional sparse representations fully automatically, so it is difficult to reflect the intention of a user in the generation process.…”

“…Then, the resulting vector fields are added to the fluid simulation to get the output Data-Driven Approaches: Deep learning-based approaches stochastically generate complex natural images such as human faces from a distribution represented by a given training set 20 and 3D terrain fields. 21 However, in general, the input data are abstracted into high-dimensional sparse representations fully automatically, so it is difficult to reflect the intention of a user in the generation process. To ensure that a user's intention is reflected in the generation process, studies have typically used a painting interaction (e.g., brushing, copy, and paste), which allows users to adjust the output appearance with user drawings while preserving the realism of the generated results.…”

TileGAN

“…In computer graphics, recent papers apply GANs to the synthesis of caricatures of human faces [Cao et al 2018], the synthesis of human avatars from a single image [Nagano et al 2018], texture and geometry synthesis of building details [Kelly et al 2018], surface-based modeling of shapes [Ben-Hamu et al 2018] and the volumetric modeling of shapes [Wang et al 2018a]. The most related problem to our work is the problem of terrain synthesis [Guérin et al 2017].…”

An Anticipation Experiment for Plate Tectonics

“…These generative models have been widely used in computer vision and computer graphics to produce natural images of animals and clothing items (Isola et al, 2017) but also to sample output of physical processes like terrain (Guerin et al, 2017).…”