On Demand Solid Texture Synthesis Using Deep 3D Networks

Abstract

This paper describes a novel approach for on demand volumetric texture synthesis based on a deep learning framework that allows for the generation of high quality 3D data at interactive rates. Based on a few example images of textures, a generative network is trained to synthesize coherent portions of solid textures of arbitrary sizes that reproduce the visual characteristics of the examples along some directions. To cope with memory limitations and computation complexity that are inherent to both high resolution and 3D processing on the GPU, only 2D textures referred to as "slices" are generated during the training stage. These synthetic textures are compared to exemplar images via a perceptual loss function based on a pre-trained deep network. The proposed network is very light (less than 100k parameters), therefore it only requires sustainable training (i.e. few hours) and is capable of very fast generation (around a second for $256^3$ voxels) on a single GPU. Integrated with a spatially seeded PRNG the proposed generator network directly returns an RGB value given a set of 3D coordinates. The synthesized volumes have good visual results that are at least equivalent to the state-of-the-art patch based approaches. They are naturally seamlessly tileable and can be fully generated in parallel.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• Universal Style Transfer via Feature Transforms
• Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
• Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses
• Non-Stationary Texture Synthesis by Adversarial Expansion
• Order-Independent Texture Synthesis
• Diversified Texture Synthesis with Feed-forward Networks
• Texture Synthesis Through Convolutional Neural Networks and Spectrum Constraints
• Incorporating long-range consistency in CNN-based texture generation

Cited by in corpus (3)

• 3D microstructural generation from 2D images of cement paste using generative adversarial networks
• A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributions
• STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?