Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.08310 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914677598978048 |
|---|---|
| author | Pöllabauer, Thomas Kühn, Julius Li, Jiayi Kuijper, Arjan |
| author_facet | Pöllabauer, Thomas Kühn, Julius Li, Jiayi Kuijper, Arjan |
| contents | Estimating the 3D shape of an object using a single image is a difficult problem. Modern approaches achieve good results for general objects, based on real photographs, but worse results on less expressive representations such as historic sketches. Our automated approach generates a variety of detailed 3D representation from a single sketch, depicting a medieval statue, and can be guided by multi-modal inputs, such as text prompts. It relies solely on synthetic data for training, making it adoptable even in cases of only small numbers of training examples. Our solution allows domain experts such as a curators to interactively reconstruct potential appearances of lost artifacts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_08310 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | One-to-many Reconstruction of 3D Geometry of cultural Artifacts using a synthetically trained Generative Model Pöllabauer, Thomas Kühn, Julius Li, Jiayi Kuijper, Arjan Computer Vision and Pattern Recognition Artificial Intelligence Estimating the 3D shape of an object using a single image is a difficult problem. Modern approaches achieve good results for general objects, based on real photographs, but worse results on less expressive representations such as historic sketches. Our automated approach generates a variety of detailed 3D representation from a single sketch, depicting a medieval statue, and can be guided by multi-modal inputs, such as text prompts. It relies solely on synthetic data for training, making it adoptable even in cases of only small numbers of training examples. Our solution allows domain experts such as a curators to interactively reconstruct potential appearances of lost artifacts. |
| title | One-to-many Reconstruction of 3D Geometry of cultural Artifacts using a synthetically trained Generative Model |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2402.08310 |