Saved in:
Bibliographic Details
Main Authors: Talwar, Abhimanyu, Laasri, Julien
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