Gaussian Material Synthesis
This work addresses the bottleneck of slow material rendering for users in computer graphics, offering a practical solution that reduces modeling time and enhances accessibility, though it is incremental in improving existing synthesis methods.
The paper tackles the slow rendering times in material synthesis workflows by introducing a neural network that provides real-time, high-quality image predictions, enabling both novice and expert users to generate hundreds of material models efficiently, with workflow timings showing scalability against Disney's principled shader.
We present a learning-based system for rapid mass-scale material synthesis that is useful for novice and expert users alike. The user preferences are learned via Gaussian Process Regression and can be easily sampled for new recommendations. Typically, each recommendation takes 40-60 seconds to render with global illumination, which makes this process impracticable for real-world workflows. Our neural network eliminates this bottleneck by providing high-quality image predictions in real time, after which it is possible to pick the desired materials from a gallery and assign them to a scene in an intuitive manner. Workflow timings against Disney's "principled" shader reveal that our system scales well with the number of sought materials, thus empowering even novice users to generate hundreds of high-quality material models without any expertise in material modeling. Similarly, expert users experience a significant decrease in the total modeling time when populating a scene with materials. Furthermore, our proposed solution also offers controllable recommendations and a novel latent space variant generation step to enable the real-time fine-tuning of materials without requiring any domain expertise.