Three-Dimensional Shape Reconstruction from Digital Freehand Design Sketching Based on Deep Learning Techniques
This paper proposes a method for 3D reconstruction from Freehand Design Sketching (FDS) in architecture and industrial design. The implementation begins by extracting features from the FDS using the self-supervised learning model DINO, followed by the continuous Signed Distance Function (SDF) regres...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/24/11717 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846105988323606528 |
|---|---|
| author | Ding Zhou Guohua Wei Xiaojun Yuan |
| author_facet | Ding Zhou Guohua Wei Xiaojun Yuan |
| author_sort | Ding Zhou |
| collection | DOAJ |
| description | This paper proposes a method for 3D reconstruction from Freehand Design Sketching (FDS) in architecture and industrial design. The implementation begins by extracting features from the FDS using the self-supervised learning model DINO, followed by the continuous Signed Distance Function (SDF) regression as an implicit representation through a Multi-Layer Perceptron network. Taking eyeglass frames as an example, the 2D contour and freehand sketch optimize the alignment by their geometrical similarity while exploiting symmetry to improve reconstruction accuracy. Experiments demonstrate that this method can effectively reconstruct high-quality 3D models of eyeglass frames from 2D freehand sketches, outperforming existing deep learning-based 3D reconstruction methods. This research offers practical information for understanding 3D modeling methodology for FDS, triggering multiple modes of design creativity and efficient scheme adjustments in industrial or architectural conceptual design. In conclusion, this novel approach integrates self-supervised learning and geometric optimization to achieve unprecedented fidelity in 3D reconstruction from FDS, setting a new benchmark for AI-driven design processes in industrial and architectural applications. |
| format | Article |
| id | doaj-art-5ac984c93f5e44a3a8164744a8d51a4e |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-5ac984c93f5e44a3a8164744a8d51a4e2024-12-27T14:08:09ZengMDPI AGApplied Sciences2076-34172024-12-0114241171710.3390/app142411717Three-Dimensional Shape Reconstruction from Digital Freehand Design Sketching Based on Deep Learning TechniquesDing Zhou0Guohua Wei1Xiaojun Yuan2School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen 518051, ChinaSchool of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen 518051, ChinaNational Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu 611731, ChinaThis paper proposes a method for 3D reconstruction from Freehand Design Sketching (FDS) in architecture and industrial design. The implementation begins by extracting features from the FDS using the self-supervised learning model DINO, followed by the continuous Signed Distance Function (SDF) regression as an implicit representation through a Multi-Layer Perceptron network. Taking eyeglass frames as an example, the 2D contour and freehand sketch optimize the alignment by their geometrical similarity while exploiting symmetry to improve reconstruction accuracy. Experiments demonstrate that this method can effectively reconstruct high-quality 3D models of eyeglass frames from 2D freehand sketches, outperforming existing deep learning-based 3D reconstruction methods. This research offers practical information for understanding 3D modeling methodology for FDS, triggering multiple modes of design creativity and efficient scheme adjustments in industrial or architectural conceptual design. In conclusion, this novel approach integrates self-supervised learning and geometric optimization to achieve unprecedented fidelity in 3D reconstruction from FDS, setting a new benchmark for AI-driven design processes in industrial and architectural applications.https://www.mdpi.com/2076-3417/14/24/11717freehand design sketching3D shape reconstructiondeep learninggeometric reconstruction algorithmsimage processing techniques |
| spellingShingle | Ding Zhou Guohua Wei Xiaojun Yuan Three-Dimensional Shape Reconstruction from Digital Freehand Design Sketching Based on Deep Learning Techniques Applied Sciences freehand design sketching 3D shape reconstruction deep learning geometric reconstruction algorithms image processing techniques |
| title | Three-Dimensional Shape Reconstruction from Digital Freehand Design Sketching Based on Deep Learning Techniques |
| title_full | Three-Dimensional Shape Reconstruction from Digital Freehand Design Sketching Based on Deep Learning Techniques |
| title_fullStr | Three-Dimensional Shape Reconstruction from Digital Freehand Design Sketching Based on Deep Learning Techniques |
| title_full_unstemmed | Three-Dimensional Shape Reconstruction from Digital Freehand Design Sketching Based on Deep Learning Techniques |
| title_short | Three-Dimensional Shape Reconstruction from Digital Freehand Design Sketching Based on Deep Learning Techniques |
| title_sort | three dimensional shape reconstruction from digital freehand design sketching based on deep learning techniques |
| topic | freehand design sketching 3D shape reconstruction deep learning geometric reconstruction algorithms image processing techniques |
| url | https://www.mdpi.com/2076-3417/14/24/11717 |
| work_keys_str_mv | AT dingzhou threedimensionalshapereconstructionfromdigitalfreehanddesignsketchingbasedondeeplearningtechniques AT guohuawei threedimensionalshapereconstructionfromdigitalfreehanddesignsketchingbasedondeeplearningtechniques AT xiaojunyuan threedimensionalshapereconstructionfromdigitalfreehanddesignsketchingbasedondeeplearningtechniques |