SyntheticFur dataset for neural rendering

TL;DR

SyntheticFur is a new dataset of synthetic fur images and simulations designed to advance neural rendering techniques, enabling more realistic fur graphics through machine learning.

Contribution

The paper introduces SyntheticFur, a large-scale dataset with synthetic fur renders and simulations, facilitating research in neural rendering for fur graphics.

Findings

Neural rendering with SyntheticFur improves fur realism.

The dataset enables training of GANs for fur image synthesis.

High fidelity fur renders can be generated from inexpensive inputs.

Abstract

We introduce a new dataset called SyntheticFur built specifically for machine learning training. The dataset consists of ray traced synthetic fur renders with corresponding rasterized input buffers and simulation data files. We procedurally generated approximately 140,000 images and 15 simulations with Houdini. The images consist of fur groomed with different skin primitives and move with various motions in a predefined set of lighting environments. We also demonstrated how the dataset could be used with neural rendering to significantly improve fur graphics using inexpensive input buffers by training a conditional generative adversarial network with perceptual loss. We hope the availability of such high fidelity fur renders will encourage new advances with neural rendering for a variety of applications.