PVP-Recon: Progressive View Planning via Warping Consistency for Sparse-View Surface Reconstruction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913494043983872 |
|---|---|
| author | Ye, Sheng He, Yuze Lin, Matthieu Sheng, Jenny Fan, Ruoyu Han, Yiheng Hu, Yubin Yi, Ran Wen, Yu-Hui Liu, Yong-Jin Wang, Wenping |
| author_facet | Ye, Sheng He, Yuze Lin, Matthieu Sheng, Jenny Fan, Ruoyu Han, Yiheng Hu, Yubin Yi, Ran Wen, Yu-Hui Liu, Yong-Jin Wang, Wenping |
| contents | Neural implicit representations have revolutionized dense multi-view surface reconstruction, yet their performance significantly diminishes with sparse input views. A few pioneering works have sought to tackle the challenge of sparse-view reconstruction by leveraging additional geometric priors or multi-scene generalizability. However, they are still hindered by the imperfect choice of input views, using images under empirically determined viewpoints to provide considerable overlap. We propose PVP-Recon, a novel and effective sparse-view surface reconstruction method that progressively plans the next best views to form an optimal set of sparse viewpoints for image capturing. PVP-Recon starts initial surface reconstruction with as few as 3 views and progressively adds new views which are determined based on a novel warping score that reflects the information gain of each newly added view. This progressive view planning progress is interleaved with a neural SDF-based reconstruction module that utilizes multi-resolution hash features, enhanced by a progressive training scheme and a directional Hessian loss. Quantitative and qualitative experiments on three benchmark datasets show that our framework achieves high-quality reconstruction with a constrained input budget and outperforms existing baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05474 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PVP-Recon: Progressive View Planning via Warping Consistency for Sparse-View Surface Reconstruction Ye, Sheng He, Yuze Lin, Matthieu Sheng, Jenny Fan, Ruoyu Han, Yiheng Hu, Yubin Yi, Ran Wen, Yu-Hui Liu, Yong-Jin Wang, Wenping Computer Vision and Pattern Recognition Graphics Neural implicit representations have revolutionized dense multi-view surface reconstruction, yet their performance significantly diminishes with sparse input views. A few pioneering works have sought to tackle the challenge of sparse-view reconstruction by leveraging additional geometric priors or multi-scene generalizability. However, they are still hindered by the imperfect choice of input views, using images under empirically determined viewpoints to provide considerable overlap. We propose PVP-Recon, a novel and effective sparse-view surface reconstruction method that progressively plans the next best views to form an optimal set of sparse viewpoints for image capturing. PVP-Recon starts initial surface reconstruction with as few as 3 views and progressively adds new views which are determined based on a novel warping score that reflects the information gain of each newly added view. This progressive view planning progress is interleaved with a neural SDF-based reconstruction module that utilizes multi-resolution hash features, enhanced by a progressive training scheme and a directional Hessian loss. Quantitative and qualitative experiments on three benchmark datasets show that our framework achieves high-quality reconstruction with a constrained input budget and outperforms existing baselines. |
| title | PVP-Recon: Progressive View Planning via Warping Consistency for Sparse-View Surface Reconstruction |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2409.05474 |