Leveraging VLM-Based Pipelines to Annotate 3D Objects

Pretrained vision language models (VLMs) present an opportunity to caption unlabeled 3D objects at scale. The leading approach to summarize VLM descriptions from different views of an object (Luo et al., 2023) relies on a language model (GPT4) to produce the final output. This text-based aggregation...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Kabra, Rishabh, Matthey, Loic, Lerchner, Alexander, Mitra, Niloy J
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!