3D colored object reconstruction from a single view image through diffusion

Li, Bo, Wei, Xiaolin, Liu, Bin, Wang, Weiming, He, Zhi-Fen and Lai, Yu-Kun ORCID: https://orcid.org/0000-0002-2094-5680 2024. 3D colored object reconstruction from a single view image through diffusion. Expert Systems with Applications 252 (Part B) , 124225. 10.1016/j.eswa.2024.124225 Item availability restricted.

PDF - Accepted Post-Print Version Restricted to Repository staff only until 15 May 2026 due to copyright restrictions. Download (12MB)

Abstract

In this paper we propose a novel 3D colored object reconstruction method from a single view image. Given a reference image, a conditional diffusion probabilistic model is built to reconstruct both a 3D point cloud shape and the corresponding color features at each point, and then images from arbitrary views can be synthesized using a volume rendering technique. The approach involves several sequential steps. First, the reference RGB image is encoded into separate shape and color latent variables. Then, a shape prediction module predicts reverse geometric noise based on the shape latent variable within the diffusion model. Next, a color prediction module predicts color features for each 3D point using information from the color latent variable. Finally, a volume rendering module transforms the generated colored point cloud into 2D image space, facilitating training based solely on a reference image. Experimental results demonstrate that the proposed method achieves competitive performance on colored 3D shape reconstruction and novel view image synthesis.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Elsevier
ISSN:	0957-4174
Date of First Compliant Deposit:	30 May 2024
Date of Acceptance:	11 May 2024
Last Modified:	22 Jun 2024 01:59
URI:	https://orca.cardiff.ac.uk/id/eprint/169271

Actions (repository staff only)

Edit Item