Retargeting Visual Data with Deformation Fields
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929449731096576 |
|---|---|
| author | Elsner, Tim Berger, Julia Wu, Tong Czech, Victor Gao, Lin Kobbelt, Leif |
| author_facet | Elsner, Tim Berger, Julia Wu, Tong Czech, Victor Gao, Lin Kobbelt, Leif |
| contents | Seam carving is an image editing method that enable content-aware resizing, including operations like removing objects. However, the seam-finding strategy based on dynamic programming or graph-cut limits its applications to broader visual data formats and degrees of freedom for editing. Our observation is that describing the editing and retargeting of images more generally by a displacement field yields a generalisation of content-aware deformations. We propose to learn a deformation with a neural network that keeps the output plausible while trying to deform it only in places with low information content. This technique applies to different kinds of visual data, including images, 3D scenes given as neural radiance fields, or even polygon meshes. Experiments conducted on different visual data show that our method achieves better content-aware retargeting compared to previous methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_13297 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Retargeting Visual Data with Deformation Fields Elsner, Tim Berger, Julia Wu, Tong Czech, Victor Gao, Lin Kobbelt, Leif Computer Vision and Pattern Recognition Seam carving is an image editing method that enable content-aware resizing, including operations like removing objects. However, the seam-finding strategy based on dynamic programming or graph-cut limits its applications to broader visual data formats and degrees of freedom for editing. Our observation is that describing the editing and retargeting of images more generally by a displacement field yields a generalisation of content-aware deformations. We propose to learn a deformation with a neural network that keeps the output plausible while trying to deform it only in places with low information content. This technique applies to different kinds of visual data, including images, 3D scenes given as neural radiance fields, or even polygon meshes. Experiments conducted on different visual data show that our method achieves better content-aware retargeting compared to previous methods. |
| title | Retargeting Visual Data with Deformation Fields |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.13297 |