Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.00829 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913488372236288 |
|---|---|
| author | Mathur, Aradhya N. Khattar, Apoorv Sharma, Ojaswa |
| author_facet | Mathur, Aradhya N. Khattar, Apoorv Sharma, Ojaswa |
| contents | In this work, we present a novel approach for reconstructing shape point clouds using planar sparse cross-sections with the help of generative modeling. We present unique challenges pertaining to the representation and reconstruction in this problem setting. Most methods in the classical literature lack the ability to generalize based on object class and employ complex mathematical machinery to reconstruct reliable surfaces. We present a simple learnable approach to generate a large number of points from a small number of input cross-sections over a large dataset. We use a compact parametric polyline representation using adaptive splitting to represent the cross-sections and perform learning using a Graph Neural Network to reconstruct the underlying shape in an adaptive manner reducing the dependence on the number of cross-sections provided. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00829 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Curvy: A Parametric Cross-section based Surface Reconstruction Mathur, Aradhya N. Khattar, Apoorv Sharma, Ojaswa Computer Vision and Pattern Recognition Computational Geometry Graphics In this work, we present a novel approach for reconstructing shape point clouds using planar sparse cross-sections with the help of generative modeling. We present unique challenges pertaining to the representation and reconstruction in this problem setting. Most methods in the classical literature lack the ability to generalize based on object class and employ complex mathematical machinery to reconstruct reliable surfaces. We present a simple learnable approach to generate a large number of points from a small number of input cross-sections over a large dataset. We use a compact parametric polyline representation using adaptive splitting to represent the cross-sections and perform learning using a Graph Neural Network to reconstruct the underlying shape in an adaptive manner reducing the dependence on the number of cross-sections provided. |
| title | Curvy: A Parametric Cross-section based Surface Reconstruction |
| topic | Computer Vision and Pattern Recognition Computational Geometry Graphics |
| url | https://arxiv.org/abs/2409.00829 |