Deep Generative Framework for Interactive 3D Terrain Authoring and Manipulation

TL;DR

This paper introduces a novel deep generative framework combining VAE and conditional GANs for interactive, realistic 3D terrain authoring, enabling diverse and interpolated terrain generation from minimal user input.

Contribution

It presents a new example-based terrain generation method using a learned latent space, improving diversity and realism over existing techniques.

Findings

Generated terrains closely resemble real-world data.

Framework enables interpolation between terrains.

Interactive tool allows minimalist user inputs for diverse outputs.

Abstract

Automated generation and (user) authoring of the realistic virtual terrain is most sought for by the multimedia applications like VR models and gaming. The most common representation adopted for terrain is Digital Elevation Model (DEM). Existing terrain authoring and modeling techniques have addressed some of these and can be broadly categorized as: procedural modeling, simulation method, and example-based methods. In this paper, we propose a novel realistic terrain authoring framework powered by a combination of VAE and generative conditional GAN model. Our framework is an example-based method that attempts to overcome the limitations of existing methods by learning a latent space from a real-world terrain dataset. This latent space allows us to generate multiple variants of terrain from a single input as well as interpolate between terrains while keeping the generated terrains close to real-world data distribution. We also developed an interactive tool, that lets the user generate diverse terrains with minimalist inputs. We perform thorough qualitative and quantitative analysis and provide comparisons with other SOTA methods. We intend to release our code/tool to the academic community.