FurnSet: Exploiting Repeats for 3D Scene Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910156880609280 |
|---|---|
| author | Dobre, Paul Wang, Xin Yang, Hongzhou |
| author_facet | Dobre, Paul Wang, Xin Yang, Hongzhou |
| contents | Single-view 3D scene reconstruction involves inferring both object geometry and spatial layout. Existing methods typically reconstruct objects independently or rely on implicit scene context, failing to exploit the repeated instances commonly present in realworld scenes. We propose FurnSet, a framework that explicitly identifies and leverages repeated object instances to improve reconstruction. Our method introduces per-object CLS tokens and a set-aware self-attention mechanism that groups identical instances and aggregates complementary observations across them, enabling joint reconstruction. We further combine scene-level and object-level conditioning to guide object reconstruction, followed by layout optimization using object point clouds with 3D and 2D projection losses for scene alignment. Experiments on 3D-Future and 3D-Front demonstrate improved scene reconstruction quality, highlighting the effectiveness of exploiting repetition for robust 3D scene reconstruction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20093 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FurnSet: Exploiting Repeats for 3D Scene Reconstruction Dobre, Paul Wang, Xin Yang, Hongzhou Computer Vision and Pattern Recognition Single-view 3D scene reconstruction involves inferring both object geometry and spatial layout. Existing methods typically reconstruct objects independently or rely on implicit scene context, failing to exploit the repeated instances commonly present in realworld scenes. We propose FurnSet, a framework that explicitly identifies and leverages repeated object instances to improve reconstruction. Our method introduces per-object CLS tokens and a set-aware self-attention mechanism that groups identical instances and aggregates complementary observations across them, enabling joint reconstruction. We further combine scene-level and object-level conditioning to guide object reconstruction, followed by layout optimization using object point clouds with 3D and 2D projection losses for scene alignment. Experiments on 3D-Future and 3D-Front demonstrate improved scene reconstruction quality, highlighting the effectiveness of exploiting repetition for robust 3D scene reconstruction. |
| title | FurnSet: Exploiting Repeats for 3D Scene Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.20093 |