NViSII: A Scriptable Tool for Photorealistic Image Generation
This provides a scriptable tool for researchers in computer vision and deep learning to create photorealistic synthetic data, though it is incremental as it builds on existing rendering technologies.
The authors tackled the problem of generating high-quality synthetic images for computer vision research by developing NViSII, a Python-based renderer using NVIDIA's OptiX ray tracing and AI denoiser, which improved sim-to-real transfer performance for object detection and pose estimation in challenging scenarios.
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 containing object meshes, materials, textures, lighting, volumetric data (e.g., smoke), and backgrounds. Metadata, such as 2D/3D bounding boxes, segmentation masks, depth maps, normal maps, material properties, and optical flow vectors, can also be generated. In this work, we discuss design goals, architecture, and performance. We demonstrate the use of data generated by path tracing for training an object detector and pose estimator, showing improved performance in sim-to-real transfer in situations that are difficult for traditional raster-based renderers. We offer this tool as an easy-to-use, performant, high-quality renderer for advancing research in synthetic data generation and deep learning.