Deep Tiling: Texture Tile Synthesis Using a Deep Learning Approach

TL;DR

This paper introduces Deep Tiling, a deep learning-based method for synthesizing large, high-resolution texture tiles from small input textures, overcoming memory limitations and improving visual quality in 3D texturing.

Contribution

It presents a novel deep learning approach for creating large texture tiles of arbitrary resolution that are structurally similar to input textures, with reduced memory requirements.

Findings

Enables synthesis of large textures beyond GPU memory limits.

Produces visually coherent texture tiles that match input structure.

Efficiently fills missing parts of large textures.

Abstract

Texturing is a fundamental process in computer graphics. Texture is leveraged to enhance the visualization outcome for a 3D scene. In many cases a texture image cannot cover a large 3D model surface because of its small resolution. Conventional techniques like repeating, mirror repeating or clamp to edge do not yield visually acceptable results. Deep learning based texture synthesis has proven to be very effective in such cases. All deep texture synthesis methods trying to create larger resolution textures are limited in terms of GPU memory resources. In this paper, we propose a novel approach to example-based texture synthesis by using a robust deep learning process for creating tiles of arbitrary resolutions that resemble the structural components of an input texture. In this manner, our method is firstly much less memory limited owing to the fact that a new texture tile of small size is synthesized and merged with the original texture and secondly can easily produce missing parts of a large texture.