3DCoMPaT$^{++}$: An improved Large-scale 3D Vision Dataset for Compositional Recognition
This dataset addresses the need for compositional recognition in 3D vision research, though it is incremental as it builds upon existing datasets by expanding scale and annotations.
The authors introduced 3DCoMPaT++, a large-scale multimodal 2D/3D dataset with 160 million rendered views and over 10 million stylized 3D shapes, annotated at the part-instance level, and proposed a new task called Grounded CoMPaT Recognition (GCR) for recognizing and grounding material compositions on 3D object parts.
In this work, we present 3DCoMPaT$^{++}$, a multimodal 2D/3D dataset with 160 million rendered views of more than 10 million stylized 3D shapes carefully annotated at the part-instance level, alongside matching RGB point clouds, 3D textured meshes, depth maps, and segmentation masks. 3DCoMPaT$^{++}$ covers 41 shape categories, 275 fine-grained part categories, and 293 fine-grained material classes that can be compositionally applied to parts of 3D objects. We render a subset of one million stylized shapes from four equally spaced views as well as four randomized views, leading to a total of 160 million renderings. Parts are segmented at the instance level, with coarse-grained and fine-grained semantic levels. We introduce a new task, called Grounded CoMPaT Recognition (GCR), to collectively recognize and ground compositions of materials on parts of 3D objects. Additionally, we report the outcomes of a data challenge organized at CVPR2023, showcasing the winning method's utilization of a modified PointNet$^{++}$ model trained on 6D inputs, and exploring alternative techniques for GCR enhancement. We hope our work will help ease future research on compositional 3D Vision.