# Deep Generative Framework for Interactive 3D Terrain Authoring and Manipulation

arXiv: https://arxiv.org/abs/2201.02369 · HTML: https://mlsanity.com/paper/2201.02369/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 7 Jan 2022.

## Builds on (most cited first, 8 of 8)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Mask-Guided Portrait Editing with Conditional GANs](https://mlsanity.com/paper/1905.10346/) (2019)
- [Deep Generation of Face Images from Sketches](https://mlsanity.com/paper/2006.01047/) (2020)
- [AFN: Attentional Feedback Network based 3D Terrain Super-Resolution](https://mlsanity.com/paper/2010.01626/) (2020)
- [Feedback Neural Network based Super-resolution of DEM for generating high fidelity features](https://mlsanity.com/paper/2007.01940/) (2020)

## Built on by (most cited first, 1 of 1)

- [StyleDEM: a Versatile Model for Authoring Terrains](https://mlsanity.com/paper/2304.09626/) (2023)

## Abstract (arXiv)

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.