Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.03713 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908392848621568 |
|---|---|
| author | Bahrami, Sam Campbell, Dylan |
| author_facet | Bahrami, Sam Campbell, Dylan |
| contents | Feed-forward 3D reconstruction methods aim to predict the 3D structure of a scene directly from input images, providing a faster alternative to per-scene optimization approaches. Significant progress has been made in single-view and few-view reconstruction using learned priors that infer object shape and appearance, even for unobserved regions. However, there is substantial potential to enhance these methods by better leveraging information from multiple views when available. To address this, we propose a few-view reconstruction model that more effectively harnesses multi-view information. Our approach introduces a simple mechanism that connects the 3D representation with pixel rays from the input views, allowing for preferential sharing of information between nearby 3D locations and between 3D locations and nearby pixel rays. We achieve this by defining the 3D representation as a set of structured, feature-augmented lines; the PlückeRF representation. Using this representation, we demonstrate improvements in reconstruction quality over the equivalent triplane representation and state-of-the-art feedforward reconstruction methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03713 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PlückeRF: A Line-based 3D Representation for Few-view Reconstruction Bahrami, Sam Campbell, Dylan Computer Vision and Pattern Recognition Feed-forward 3D reconstruction methods aim to predict the 3D structure of a scene directly from input images, providing a faster alternative to per-scene optimization approaches. Significant progress has been made in single-view and few-view reconstruction using learned priors that infer object shape and appearance, even for unobserved regions. However, there is substantial potential to enhance these methods by better leveraging information from multiple views when available. To address this, we propose a few-view reconstruction model that more effectively harnesses multi-view information. Our approach introduces a simple mechanism that connects the 3D representation with pixel rays from the input views, allowing for preferential sharing of information between nearby 3D locations and between 3D locations and nearby pixel rays. We achieve this by defining the 3D representation as a set of structured, feature-augmented lines; the PlückeRF representation. Using this representation, we demonstrate improvements in reconstruction quality over the equivalent triplane representation and state-of-the-art feedforward reconstruction methods. |
| title | PlückeRF: A Line-based 3D Representation for Few-view Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.03713 |