DC3DO：用於3D物體的擴散分類器

DC3DO: Diffusion Classifier for 3D Objects

August 13, 2024

作者: Nursena Koprucu, Meher Shashwat Nigam, Shicheng Xu, Biruk Abere, Gabriele Dominici, Andrew Rodriguez, Sharvaree Vadgam, Berfin Inal, Alberto Tono

cs.AI

摘要

受 Geoffrey Hinton 強調生成建模的啟發，即「要認識形狀，首先要學會生成它們」，我們探索了使用 3D 擴散模型進行物體分類的方法。利用這些模型的密度估計，我們的方法，即用於 3D 物體的擴散分類器（DC3DO），實現了無需額外訓練即可對 3D 形狀進行分類。平均而言，我們的方法相較於其多視圖對應物有 12.5% 的改善，展現了比辨識方法更優越的多模態推理能力。DC3DO 使用在 ShapeNet 上訓練的類條件擴散模型，我們對椅子和汽車的點雲進行推論。這項工作突顯了生成模型在 3D 物體分類中的潛力。

English

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.