Vastextures: Vast repository of textures and PBR materials extracted from real-world images using unsupervised methods

TL;DR

Vastextures is a large, diverse, and automatically extracted repository of real-world textures and PBR materials, designed to support AI training and virtual world creation with less refined but highly varied assets.

Contribution

The paper introduces Vastextures, a massive unsupervised method for extracting diverse real-world textures and PBR materials from natural images, expanding asset availability for AI and virtual worlds.

Findings

Outperforms existing repositories in AI training tasks

Contains 500,000 diverse textures and materials

Includes emergent properties in extracted PBR materials

Abstract

Vastextures is a vast repository of 500,000 textures and PBR materials extracted from real-world images using an unsupervised process. The extracted materials and textures are extremely diverse and cover a vast range of real-world patterns, but at the same time less refined compared to existing repositories. The repository is composed of 2D textures cropped from natural images and SVBRDF/PBR materials generated from these textures. Textures and PBR materials are essential for CGI. Existing materials repositories focus on games, animation, and arts, that demand a limited amount of high-quality assets. However, virtual worlds and synthetic data are becoming increasingly important for training A.I systems for computer vision. This application demands a huge amount of diverse assets but at the same time less affected by noisy and unrefined assets. Vastexture aims to address this need by creating a free, huge, and diverse assets repository that covers as many real-world materials as possible. The materials are automatically extracted from natural images in two steps: 1) Automatically scanning a giant amount of images to identify and crop regions with uniform textures. This is done by splitting the image into a grid of cells and identifying regions in which all of the cells share a similar statistical distribution. 2) Extracting the properties of the PBR material from the cropped texture. This is done by randomly guessing every correlation between the properties of the texture image and the properties of the PBR material. The resulting PBR materials exhibit a vast amount of real-world patterns as well as unexpected emergent properties. Neutral nets trained on this repository outperformed nets trained using handcrafted assets.