Scalable 3D Captioning with Pretrained Models
This addresses the challenge of scalable aptioning for 3D objects, reducing reliance on manual annotation for researchers and practitioners in 3D vision and graphics.
The paper tackles the problem of generating descriptive text for 3D objects by introducing Cap3D, an automatic approach that uses pretrained models to create captions from multiple views, resulting in 660k 3D-text pairs and surpassing human-authored descriptions in quality, cost, and speed on 41k human annotations.
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.