S3D: Sketch-Driven 3D Model Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912410658406400 |
|---|---|
| author | Song, Hail Shin, Wonsik Lee, Naeun Chung, Soomin Kwak, Nojun Woo, Woontack |
| author_facet | Song, Hail Shin, Wonsik Lee, Naeun Chung, Soomin Kwak, Nojun Woo, Woontack |
| contents | Generating high-quality 3D models from 2D sketches is a challenging task due to the inherent ambiguity and sparsity of sketch data. In this paper, we present S3D, a novel framework that converts simple hand-drawn sketches into detailed 3D models. Our method utilizes a U-Net-based encoder-decoder architecture to convert sketches into face segmentation masks, which are then used to generate a 3D representation that can be rendered from novel views. To ensure robust consistency between the sketch domain and the 3D output, we introduce a novel style-alignment loss that aligns the U-Net bottleneck features with the initial encoder outputs of the 3D generation module, significantly enhancing reconstruction fidelity. To further enhance the network's robustness, we apply augmentation techniques to the sketch dataset. This streamlined framework demonstrates the effectiveness of S3D in generating high-quality 3D models from sketch inputs. The source code for this project is publicly available at https://github.com/hailsong/S3D. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04185 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | S3D: Sketch-Driven 3D Model Generation Song, Hail Shin, Wonsik Lee, Naeun Chung, Soomin Kwak, Nojun Woo, Woontack Computer Vision and Pattern Recognition Artificial Intelligence Generating high-quality 3D models from 2D sketches is a challenging task due to the inherent ambiguity and sparsity of sketch data. In this paper, we present S3D, a novel framework that converts simple hand-drawn sketches into detailed 3D models. Our method utilizes a U-Net-based encoder-decoder architecture to convert sketches into face segmentation masks, which are then used to generate a 3D representation that can be rendered from novel views. To ensure robust consistency between the sketch domain and the 3D output, we introduce a novel style-alignment loss that aligns the U-Net bottleneck features with the initial encoder outputs of the 3D generation module, significantly enhancing reconstruction fidelity. To further enhance the network's robustness, we apply augmentation techniques to the sketch dataset. This streamlined framework demonstrates the effectiveness of S3D in generating high-quality 3D models from sketch inputs. The source code for this project is publicly available at https://github.com/hailsong/S3D. |
| title | S3D: Sketch-Driven 3D Model Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2505.04185 |