Inspired by Geoffrey Hinton emphasis on generative modeling, To recognize shapes, first learn to generate them, we explore the use of 3D diffusion models for object classification. Leveraging the density estimates from these models, our approach, the Diffusion Classifier for 3D Objects (DC3DO), enables zero-shot classification of 3D shapes without additional training. On average, our method achieves a 12.5 percent improvement compared to its multiview counterparts, demonstrating superior multimodal reasoning over discriminative approaches. DC3DO employs a class-conditional diffusion model trained on ShapeNet, and we run inferences on point clouds of chairs and cars. This work highlights the potential of generative models in 3D object classification.
@article{arxiv.2408.06693,
title = {DC3DO: Diffusion Classifier for 3D Objects},
author = {Nursena Koprucu and Meher Shashwat Nigam and Shicheng Xu and Biruk Abere and Gabriele Dominici and Andrew Rodriguez and Sharvaree Vadgama and Berfin Inal and Alberto Tono},
journal= {arXiv preprint arXiv:2408.06693},
year = {2024}
}