SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenes
This provides a tool for researchers in computer vision to automate dataset creation for amodal segmentation, though it is incremental as it builds on existing synthetic data generation methods.
The authors tackled the problem of generating synthetic datasets for unseen object amodal instance segmentation in cluttered tabletop scenes by developing SynTable, a tool that automatically produces high-quality annotated data, resulting in significantly improved Sim-to-Real transfer performance on the OSD-Amodal dataset.
In this work, we present SynTable, a unified and flexible Python-based dataset generator built using NVIDIA's Isaac Sim Replicator Composer for generating high-quality synthetic datasets for unseen object amodal instance segmentation of cluttered tabletop scenes. Our dataset generation tool can render complex 3D scenes containing object meshes, materials, textures, lighting, and backgrounds. Metadata, such as modal and amodal instance segmentation masks, object amodal RGBA instances, occlusion masks, depth maps, bounding boxes, and material properties can be automatically generated to annotate the scene according to the users' requirements. Our tool eliminates the need for manual labeling in the dataset generation process while ensuring the quality and accuracy of the dataset. In this work, we discuss our design goals, framework architecture, and the performance of our tool. We demonstrate the use of a sample dataset generated using SynTable for training a state-of-the-art model, UOAIS-Net. Our state-of-the-art results show significantly improved performance in Sim-to-Real transfer when evaluated on the OSD-Amodal dataset. We offer this tool as an open-source, easy-to-use, photorealistic dataset generator for advancing research in deep learning and synthetic data generation. The links to our source code, demonstration video, and sample dataset can be found in the supplementary materials.