Scalable 3D Captioning with Pretrained Models

Tiange Luo, Chris Rockwell, Honglak Lee, Justin Johnson

Keywords: 3D Captioning, Text-to-3D, Multi-Modal Learning

TL;DR: We introduce Cap3D, an automatic approach for generating descriptive text for 3D objects, by leveraging pretrained models in captioning, alignment, and language to consolidate multi-view information.

Abstract: We introduce Cap3D, an automatic approach for generating descriptive text for 3D objects. This approach utilizes pretrained models from image captioning, image-text alignment, and LLM to consolidate captions from multiple views of a 3D asset, completely side-stepping the time-consuming and costly process of manual annotation. We apply Cap3D to the recently introduced large-scale 3D dataset, Objaverse, resulting in 660k 3D-text pairs. Our evaluation, conducted using 41k human annotations from the same dataset, demonstrates that Cap3D surpasses human-authored descriptions in terms of quality, cost, and speed. Through effective prompt engineering, Cap3D rivals human performance in generating geometric descriptions on 17k collected annotations from the ABO dataset. Finally, we finetune Text-to-3D models on Cap3D and human captions, and show Cap3D outperforms; and benchmark the SOTA including Point·E, Shape·E, and DreamFusion.

Submission Number: 6