Deep Tiling: Texture Tile Synthesis Using a Constant Space Deep Learning Approach

EasyChair Preprint 6790

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, mirroring or clamping 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 that attempt 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 existing texture and secondly can easily produce missing parts of a large texture.

Keyphrases: CNN, Gram matrices, deep learning, texture synthesis, tiling

@booklet{EasyChair:6790,
  author    = {Vasileios Toulatzis and Ioannis Fudos},
  title     = {Deep Tiling: Texture Tile Synthesis Using a Constant Space Deep Learning Approach},
  howpublished = {EasyChair Preprint 6790},
  year      = {EasyChair, 2021}}