SyntheticFur dataset for neural rendering
This provides a specialized dataset for researchers and developers working on neural rendering of fur, though it is incremental as it focuses on a specific domain rather than a broader breakthrough.
The authors introduced the SyntheticFur dataset, containing approximately 140,000 ray-traced synthetic fur images with corresponding input buffers and simulation data, to address the need for high-fidelity training data in neural rendering. They demonstrated its utility by training a conditional GAN with perceptual loss, which significantly improved fur graphics using inexpensive input buffers.
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.