Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.14621 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908372428652544 |
|---|---|
| author | Talwar, Abhimanyu Laasri, Julien |
| author_facet | Talwar, Abhimanyu Laasri, Julien |
| contents | We consider the problem of reconstructing a 3D scene from multiple sketches. We propose a pipeline which involves (1) stitching together multiple sketches through use of correspondence points, (2) converting the stitched sketch into a realistic image using a CycleGAN, and (3) estimating that image's depth-map using a pre-trained convolutional neural network based architecture called MegaDepth. Our contribution includes constructing a dataset of image-sketch pairs, the images for which are from the Zurich Building Database, and sketches have been generated by us. We use this dataset to train a CycleGAN for our pipeline's second step. We end up with a stitching process that does not generalize well to real drawings, but the rest of the pipeline that creates a 3D reconstruction from a single sketch performs quite well on a wide variety of drawings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_14621 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 3D Reconstruction from Sketches Talwar, Abhimanyu Laasri, Julien Computer Vision and Pattern Recognition Machine Learning 68T45 I.2.10 We consider the problem of reconstructing a 3D scene from multiple sketches. We propose a pipeline which involves (1) stitching together multiple sketches through use of correspondence points, (2) converting the stitched sketch into a realistic image using a CycleGAN, and (3) estimating that image's depth-map using a pre-trained convolutional neural network based architecture called MegaDepth. Our contribution includes constructing a dataset of image-sketch pairs, the images for which are from the Zurich Building Database, and sketches have been generated by us. We use this dataset to train a CycleGAN for our pipeline's second step. We end up with a stitching process that does not generalize well to real drawings, but the rest of the pipeline that creates a 3D reconstruction from a single sketch performs quite well on a wide variety of drawings. |
| title | 3D Reconstruction from Sketches |
| topic | Computer Vision and Pattern Recognition Machine Learning 68T45 I.2.10 |
| url | https://arxiv.org/abs/2505.14621 |