computer vision machine learning
3D CoMPaT is a richly annotated large-scale dataset of rendered compositions of Materials on Parts of thousands of unique 3D Models. This dataset primarily focuses on stylizing 3D shapes at part-level with compatible materials. Each object with the applied part-material compositions is rendered from four equally spaced views as well as four randomized views. We introduce a new task, called Grounded CoMPaT Recognition (GCR), to collectively recognize and ground compositions of materials on parts of 3D objects. We present two variations of this task and adapt state-of-art 2D/3D deep learning methods to solve the problem as baselines for future research. We hope our work will help ease future research on compositional 3D Vision.
Continually improving 3D annotations and renderings
See all datasets managed by Vision-CAIR, CEMSE, KAUST.
3DCoMPaT: Composition of Materials on Parts of 3D Things was accessed on
DATE from https://registry.opendata.aws/3dcompat.
Edit this dataset entry on GitHub