FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914278750027776 |
|---|---|
| author | Zhang, Shangzhan Wang, Jianyuan Xu, Yinghao Xue, Nan Rupprecht, Christian Zhou, Xiaowei Shen, Yujun Wetzstein, Gordon |
| author_facet | Zhang, Shangzhan Wang, Jianyuan Xu, Yinghao Xue, Nan Rupprecht, Christian Zhou, Xiaowei Shen, Yujun Wetzstein, Gordon |
| contents | We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images (i.e., as few as 2-8 inputs), which is a challenging yet practical setting in real-world applications. Our solution features a cascaded learning paradigm with camera pose serving as the critical bridge, recognizing its essential role in mapping 3D structures onto 2D image planes. Concretely, FLARE starts with camera pose estimation, whose results condition the subsequent learning of geometric structure and appearance, optimized through the objectives of geometry reconstruction and novel-view synthesis. Utilizing large-scale public datasets for training, our method delivers state-of-the-art performance in the tasks of pose estimation, geometry reconstruction, and novel view synthesis, while maintaining the inference efficiency (i.e., less than 0.5 seconds). The project page and code can be found at: https://zhanghe3z.github.io/FLARE/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12138 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views Zhang, Shangzhan Wang, Jianyuan Xu, Yinghao Xue, Nan Rupprecht, Christian Zhou, Xiaowei Shen, Yujun Wetzstein, Gordon Computer Vision and Pattern Recognition We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images (i.e., as few as 2-8 inputs), which is a challenging yet practical setting in real-world applications. Our solution features a cascaded learning paradigm with camera pose serving as the critical bridge, recognizing its essential role in mapping 3D structures onto 2D image planes. Concretely, FLARE starts with camera pose estimation, whose results condition the subsequent learning of geometric structure and appearance, optimized through the objectives of geometry reconstruction and novel-view synthesis. Utilizing large-scale public datasets for training, our method delivers state-of-the-art performance in the tasks of pose estimation, geometry reconstruction, and novel view synthesis, while maintaining the inference efficiency (i.e., less than 0.5 seconds). The project page and code can be found at: https://zhanghe3z.github.io/FLARE/ |
| title | FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.12138 |