NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909556997619712 |
|---|---|
| author | Zhang, Wenyuan Jia, Emily Yue-ting Zhou, Junsheng Ma, Baorui Shi, Kanle Liu, Yu-Shen Han, Zhizhong |
| author_facet | Zhang, Wenyuan Jia, Emily Yue-ting Zhou, Junsheng Ma, Baorui Shi, Kanle Liu, Yu-Shen Han, Zhizhong |
| contents | Recently, it has shown that priors are vital for neural implicit functions to reconstruct high-quality surfaces from multi-view RGB images. However, current priors require large-scale pre-training, and merely provide geometric clues without considering the importance of color. In this paper, we present NeRFPrior, which adopts a neural radiance field as a prior to learn signed distance fields using volume rendering for surface reconstruction. Our NeRF prior can provide both geometric and color clues, and also get trained fast under the same scene without additional data. Based on the NeRF prior, we are enabled to learn a signed distance function (SDF) by explicitly imposing a multi-view consistency constraint on each ray intersection for surface inference. Specifically, at each ray intersection, we use the density in the prior as a coarse geometry estimation, while using the color near the surface as a clue to check its visibility from another view angle. For the textureless areas where the multi-view consistency constraint does not work well, we further introduce a depth consistency loss with confidence weights to infer the SDF. Our experimental results outperform the state-of-the-art methods under the widely used benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18361 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction Zhang, Wenyuan Jia, Emily Yue-ting Zhou, Junsheng Ma, Baorui Shi, Kanle Liu, Yu-Shen Han, Zhizhong Computer Vision and Pattern Recognition Recently, it has shown that priors are vital for neural implicit functions to reconstruct high-quality surfaces from multi-view RGB images. However, current priors require large-scale pre-training, and merely provide geometric clues without considering the importance of color. In this paper, we present NeRFPrior, which adopts a neural radiance field as a prior to learn signed distance fields using volume rendering for surface reconstruction. Our NeRF prior can provide both geometric and color clues, and also get trained fast under the same scene without additional data. Based on the NeRF prior, we are enabled to learn a signed distance function (SDF) by explicitly imposing a multi-view consistency constraint on each ray intersection for surface inference. Specifically, at each ray intersection, we use the density in the prior as a coarse geometry estimation, while using the color near the surface as a clue to check its visibility from another view angle. For the textureless areas where the multi-view consistency constraint does not work well, we further introduce a depth consistency loss with confidence weights to infer the SDF. Our experimental results outperform the state-of-the-art methods under the widely used benchmarks. |
| title | NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.18361 |