Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.09050 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916247145283584 |
|---|---|
| author | Chen, Mingxiang Zhang, Jian Zhou, Boli Song, Yang |
| author_facet | Chen, Mingxiang Zhang, Jian Zhou, Boli Song, Yang |
| contents | Recent advancements in deep learning for 3D models have propelled breakthroughs in generation, detection, and scene understanding. However, the effectiveness of these algorithms hinges on large training datasets. We address the challenge by introducing Efficient 3D Seam Carving (E3SC), a novel 3D model augmentation method based on seam carving, which progressively deforms only part of the input model while ensuring the overall semantics are unchanged. Experiments show that our approach is capable of producing diverse and high-quality augmented 3D shapes across various types and styles of input models, achieving considerable improvements over previous methods. Quantitative evaluations demonstrate that our method effectively enhances the novelty and quality of shapes generated by other subsequent 3D generation algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_09050 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 3D Shape Augmentation with Content-Aware Shape Resizing Chen, Mingxiang Zhang, Jian Zhou, Boli Song, Yang Computer Vision and Pattern Recognition Recent advancements in deep learning for 3D models have propelled breakthroughs in generation, detection, and scene understanding. However, the effectiveness of these algorithms hinges on large training datasets. We address the challenge by introducing Efficient 3D Seam Carving (E3SC), a novel 3D model augmentation method based on seam carving, which progressively deforms only part of the input model while ensuring the overall semantics are unchanged. Experiments show that our approach is capable of producing diverse and high-quality augmented 3D shapes across various types and styles of input models, achieving considerable improvements over previous methods. Quantitative evaluations demonstrate that our method effectively enhances the novelty and quality of shapes generated by other subsequent 3D generation algorithms. |
| title | 3D Shape Augmentation with Content-Aware Shape Resizing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.09050 |