WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917006950793216 |
|---|---|
| author | Liu, Yifan Min, Zhiyuan Wang, Zhenwei Wu, Junta Wang, Tengfei Yuan, Yixuan Luo, Yawei Guo, Chunchao |
| author_facet | Liu, Yifan Min, Zhiyuan Wang, Zhenwei Wu, Junta Wang, Tengfei Yuan, Yixuan Luo, Yawei Guo, Chunchao |
| contents | We present WorldMirror, an all-in-one, feed-forward model for versatile 3D geometric prediction tasks. Unlike existing methods constrained to image-only inputs or customized for a specific task, our framework flexibly integrates diverse geometric priors, including camera poses, intrinsics, and depth maps, while simultaneously generating multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussians. This elegant and unified architecture leverages available prior information to resolve structural ambiguities and delivers geometrically consistent 3D outputs in a single forward pass. WorldMirror achieves state-of-the-art performance across diverse benchmarks from camera, point map, depth, and surface normal estimation to novel view synthesis, while maintaining the efficiency of feed-forward inference. Code and models will be publicly available soon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10726 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting Liu, Yifan Min, Zhiyuan Wang, Zhenwei Wu, Junta Wang, Tengfei Yuan, Yixuan Luo, Yawei Guo, Chunchao Computer Vision and Pattern Recognition We present WorldMirror, an all-in-one, feed-forward model for versatile 3D geometric prediction tasks. Unlike existing methods constrained to image-only inputs or customized for a specific task, our framework flexibly integrates diverse geometric priors, including camera poses, intrinsics, and depth maps, while simultaneously generating multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussians. This elegant and unified architecture leverages available prior information to resolve structural ambiguities and delivers geometrically consistent 3D outputs in a single forward pass. WorldMirror achieves state-of-the-art performance across diverse benchmarks from camera, point map, depth, and surface normal estimation to novel view synthesis, while maintaining the efficiency of feed-forward inference. Code and models will be publicly available soon. |
| title | WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.10726 |