Frontiers of Information Technology & Electronic Engineering
>> 2024,
Volume 25,
Issue 1
doi:
10.1631/FITEE.2300314
Deep3DSketch-im: rapid high-fidelity AI 3D model generation by single freehand sketches
1. College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; 2. School of Software Technology, Zhejiang University, Hangzhou 310027, China; 3. School of Information Engineering, Huzhou University, Huzhou 313000, China;
Received: 2023-04-30
Accepted: 2024-02-19
Available online: 2024-02-19
Next
Previous
Abstract
The rise of artificial intelligence generated content (AIGC) has been remarkable in the language and image fields, but generated three-dimensional (3D) models are still under-explored due to their complex nature and lack of training data. The conventional approach of creating 3D content through computer-aided design (CAD) is labor-intensive and requires expertise, making it challenging for novice users. To address this issue, we propose a -based 3D modeling approach, Deep3D-im, which uses a single freehand for modeling. This is a challenging task due to the sparsity and ambiguity. Deep3D-im uses a novel data representation called the signed distance field (SDF) to improve the -to-3D model process by incorporating an implicit continuous field instead of voxel or points, and a specially designed neural network that can capture point and local features. Extensive experiments are conducted to demonstrate the effectiveness of the approach, achieving state-of-the-art (SOTA) performance on both synthetic and real datasets. Additionally, users show more satisfaction with results generated by Deep3D-im, as reported in a user study. We believe that Deep3D-im has the potential to revolutionize the process of 3D modeling by providing an intuitive and easy-to-use solution for novice users.
京公网安备 11010502051620号
