SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenes - Dataset and Model Weights

Ng, Zhili; Wang, Haozhe; Zhang, Zhengshen

doi:10.5281/zenodo.10565517

Published January 25, 2024 | Version 1

Dataset Open

SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenes - Dataset and Model Weights

1. National University of Singapore

The is the dataset associated with the paper "SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenes".

Files

CAD_models.zip

Files (40.4 GB)

Name	Size	Download all
CAD_models.zip md5:9a3cc1409cc97168529b1bd5d6ae4064	8.3 GB	Preview Download
experiment_model_weights.zip md5:cd49c8e08977f68977a3497157732ad4	9.9 GB	Preview Download
syntable.zip md5:32679cd49d46b7616cd3918aff662e73	22.3 GB	Preview Download

Additional details

Repository URL: https://github.com/ngzhili/SynTable
Programming language: Python
Development Status: Active

235

Views

181

Downloads

Show more details

	All versions	This version
Views	235	235
Downloads	181	181
Data volume	4.0 TB	4.0 TB

More info on how stats are collected....

DOI

Resource type

Dataset

Publisher

arXiv

License: MIT License

A short and simple permissive license with conditions only requiring preservation of copyright and license notices. Licensed works, modifications, and larger works may be distributed under different terms and without source code. Read more

Technical metadata

Created: February 5, 2024
Modified: March 25, 2025

SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenes - Dataset and Model Weights

Authors/Creators

Description

Files

CAD_models.zip

Files (40.4 GB)

Additional details

Software