OpenShape: Scaling Up3D Shape Representation Towards Open-World Understanding - Supplementary Material Anonymous Author(s) Affiliation Address email 1 More Examples of Multi-Modal 3D Shape Retrieval

We leverage the metadata from the four datasets to generate the raw texts. Objaverse:We utilize the name associated with each shape to serve as the text. In this way, we generate one or more raw texts for each shape. I am analyzing a 3D dataset with various text descriptions for the 3D models. If a text contains a clear noun (or noun phrase) that could potentially describe a 3D object, please respond with "Y".