Isaac Sim Replicator is a collection of extensions, python APIs, workflows, and tools such as Replicator Composer that enable a variety of synthetic data generation tasks.
Interacting with GUI:¶
These extensions provide UI interfaces to common tasks and examples you can interact with
Adding Randomization: Use the Domain Randomization extension to add pose, material, lighting, etc randomzation to your scene.
Generating and Training: See the Replicator Playground for a high level interactive workflow from generating data to training.
Useful Python APIs¶
Details about image based sensors: See the omni.syntheticdata extension documentation. This extension provides the core interfaces used to acquire image based synthetic data.
Standalone Python Workflows¶
Once you have configured, tested, and validated your scene’s semantic information and randomization, the following tutorials provide useful examples for different synthetic generation workflows via standalone python scripts.
Replicator Composer is a tool for creating parameterizable offline datasets in Isaac Sim.
Using Replicator Composer See the Replicator Composer tutorial for a walkthrough on how to use this tool to generate a dataset
Detailed Manual See Replicator Composer Manual for a detailed manual about Composer
Parameter List See Replicator Composer Parameter List for a detailed list of parameters you can change when using Composer