Deep Generative Framework for Interactive 3D Terrain Authoring and Manipulation
This work addresses terrain authoring for VR and gaming, offering an incremental improvement over existing example-based methods.
The paper tackles the problem of realistic virtual terrain generation for multimedia applications by proposing a deep generative framework that combines VAE and conditional GAN to learn a latent space from real-world data, enabling generation of diverse terrains with minimal user input and achieving competitive results compared to state-of-the-art methods.
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.