TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval
This addresses the problem of retrieving 3D shapes from text for applications in 3D data management, but it is incremental as it builds on existing contrastive learning methods.
The paper tackles text-to-shape retrieval by proposing a trimodal learning scheme using text, multi-view images, and 3D shape voxels with large batch contrastive learning, achieving good performance without complex attention mechanisms.
Text-to-shape retrieval is an increasingly relevant problem with the growth of 3D shape data. Recent work on contrastive losses for learning joint embeddings over multimodal data has been successful at tasks such as retrieval and classification. Thus far, work on joint representation learning for 3D shapes and text has focused on improving embeddings through modeling of complex attention between representations, or multi-task learning. We propose a trimodal learning scheme over text, multi-view images and 3D shape voxels, and show that with large batch contrastive learning we achieve good performance on text-to-shape retrieval without complex attention mechanisms or losses. Our experiments serve as a foundation for follow-up work on building trimodal embeddings for text-image-shape.