3D Mesh Editing using Masked LRMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909787485110272 |
|---|---|
| author | Gao, Will Wang, Dilin Fan, Yuchen Bozic, Aljaz Stuyck, Tuur Li, Zhengqin Dong, Zhao Ranjan, Rakesh Sarafianos, Nikolaos |
| author_facet | Gao, Will Wang, Dilin Fan, Yuchen Bozic, Aljaz Stuyck, Tuur Li, Zhengqin Dong, Zhao Ranjan, Rakesh Sarafianos, Nikolaos |
| contents | We present a novel approach to shape editing, building on recent progress in 3D reconstruction from multi-view images. We formulate shape editing as a conditional reconstruction problem, where the model must reconstruct the input shape with the exception of a specified 3D region, in which the geometry should be generated from the conditional signal. To this end, we train a conditional Large Reconstruction Model (LRM) for masked reconstruction, using multi-view consistent masks rendered from a randomly generated 3D occlusion, and using one clean viewpoint as the conditional signal. During inference, we manually define a 3D region to edit and provide an edited image from a canonical viewpoint to fill that region. We demonstrate that, in just a single forward pass, our method not only preserves the input geometry in the unmasked region through reconstruction capabilities on par with SoTA, but is also expressive enough to perform a variety of mesh edits from a single image guidance that past works struggle with, while being 2-10x faster than the top-performing prior work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_08641 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 3D Mesh Editing using Masked LRMs Gao, Will Wang, Dilin Fan, Yuchen Bozic, Aljaz Stuyck, Tuur Li, Zhengqin Dong, Zhao Ranjan, Rakesh Sarafianos, Nikolaos Computer Vision and Pattern Recognition We present a novel approach to shape editing, building on recent progress in 3D reconstruction from multi-view images. We formulate shape editing as a conditional reconstruction problem, where the model must reconstruct the input shape with the exception of a specified 3D region, in which the geometry should be generated from the conditional signal. To this end, we train a conditional Large Reconstruction Model (LRM) for masked reconstruction, using multi-view consistent masks rendered from a randomly generated 3D occlusion, and using one clean viewpoint as the conditional signal. During inference, we manually define a 3D region to edit and provide an edited image from a canonical viewpoint to fill that region. We demonstrate that, in just a single forward pass, our method not only preserves the input geometry in the unmasked region through reconstruction capabilities on par with SoTA, but is also expressive enough to perform a variety of mesh edits from a single image guidance that past works struggle with, while being 2-10x faster than the top-performing prior work. |
| title | 3D Mesh Editing using Masked LRMs |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.08641 |