NViSII: A Scriptable Tool for Photorealistic Image Generation

• Published in: arXiv.org
• Main Authors: Morrical, Nathan, Tremblay, Jonathan, Lin, Yunzhi, Tyree, Stephen, Birchfield, Stan, Pascucci, Valerio, Wald, Ingo
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 28.05.2021
• Subjects: Computer vision; Deep learning; Image processing; Image quality; Image segmentation; Material properties; Optical flow (image analysis); Optical properties; Ray tracing; Renderers

We present a Python-based renderer built on NVIDIA's OptiX ray tracing engine and the OptiX AI denoiser, designed to generate high-quality synthetic images for research in computer vision and deep learning. Our tool enables the description and manipulation of complex dynamic 3D scenes containin...