Adaptive & Multi-Resolution Procedural Infinite Terrain Generation with Diffusion Models and Perlin Noise

Aryamaan Jain, Avinash Sharma and K S Rajan

Abstract

This paper proposes a novel adaptive multi-resolution framework for generating terrains. Our framework combines diffusion-based generative network and novel frequency separated terrain features for terrain patch generation. Additionally, we propose to leverage learnable terrain super-resolution for enhancing generated terrain patch followed by novel kernel-based blending of these patches using Perlin noise to generate infinite terrain with realistic terrain features. We provide a comprehensive quantitative and qualitative evaluation of the proposed framework.

Video

Downloads

• Paper
• Code

Contact

• Aryamaan Jain: aryamaan.jain@research.iiit.ac.in
• Avinash Sharma: asharma@iiit.ac.in
• K S Rajan: rajan@iiit.ac.in

BibTeX

@inbook{10.1145/3571600.3571657
  author = {Jain, Aryamaan and Sharma, Avinash and Rajan, K S},
  title = {Adaptive & Multi-Resolution Procedural Infinite Terrain Generation with Diffusion Models and Perlin Noise},
  year = {2022},
  isbn = {9781450398220},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3571600.3571657},
  booktitle = {Proceedings of the Thirteenth Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP'22), December 8--10, 2022, Gandhinagar, India},
  articleno = {57},
  numpages = {9}
}