Realtime Texture Upsampling on Graphics Hardware Using Fractal Coding

Proceedings of International Conference on Cyberworlds 2022, pp.39-46, 2022.

Authors: Kominami Yuto and Tomohiko Mukai

Download: [preprint] [slides] [code]

Abstract: The texture upsampling technique reduces the memory and manual labor required to create a high-definition texture by procedurally increasing the image resolution on the fly. We propose a real-time texture upsampling technique that utilizes an underlying fractal structure of surface textures found in natural phenomena, such as stone surfaces, tree bark, and animal skin. Our method encodes the source texture by a fractal compression technique in the authoring process. The cross-scale correspondences between two mipmap layers are encoded as compact fractal codes and packed in three types of GPU-friendly formats. The runtime computation increases the resolution of encoded textures by recursively applying fractal decoding. Owing to the concurrent data structures, texture upsampling by any power of 2 is efficiently executed on GPUs. Furthermore, we propose an iterative algorithm to refine the fractal code, thus improving upsampling quality. We demonstrate the effectiveness of our proposed algorithm by synthesizing a high-resolution texture with semi-random patterns.

Acknowledgements: This work was supported by PlatinumGames Inc.

©2022 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. https://doi.org/10.1109/CW55638.2022.00015