PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding
This provides a foundational resource for researchers in 3D computer vision, enabling tasks such as shape analysis and dynamic scene modeling, though it is incremental as it builds on existing datasets and methods.
The authors introduced PartNet, a large-scale dataset of 3D objects with fine-grained, hierarchical part annotations, consisting of 573,585 part instances over 26,671 models across 24 categories, and used it to benchmark tasks like semantic and instance segmentation, proposing a novel method that outperformed existing ones.
We present PartNet: a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. Our dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories. This dataset enables and serves as a catalyst for many tasks such as shape analysis, dynamic 3D scene modeling and simulation, affordance analysis, and others. Using our dataset, we establish three benchmarking tasks for evaluating 3D part recognition: fine-grained semantic segmentation, hierarchical semantic segmentation, and instance segmentation. We benchmark four state-of-the-art 3D deep learning algorithms for fine-grained semantic segmentation and three baseline methods for hierarchical semantic segmentation. We also propose a novel method for part instance segmentation and demonstrate its superior performance over existing methods.