High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representation
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_ | 1866914412164546560 |
|---|---|
| author | Yang, Tongyu Guo, Heng Matsushita, Yasuyuki Okura, Fumio Luo, Yu Fan, Xin |
| author_facet | Yang, Tongyu Guo, Heng Matsushita, Yasuyuki Okura, Fumio Luo, Yu Fan, Xin |
| contents | Previous multi-view normal integration methods typically sample a single ray per pixel, without considering the spatial area covered by each pixel, which varies with camera intrinsics and the camera-to-object distance. Consequently, when the target object is captured at different distances, the normals at corresponding pixels may differ across views. This multi-view surface normal inconsistency results in the blurring of high-frequency details in the reconstructed surface. To address this issue, we propose a scale-encoded neural surface representation that incorporates the pixel coverage area into the neural representation. By associating each 3D point with a spatial scale and calculating its normal from a hybrid grid-based encoding, our method effectively represents multi-scale surface normals captured at varying distances. Furthermore, to enable scale-aware surface reconstruction, we introduce a mesh extraction module that assigns an optimal local scale to each vertex based on the training observations. Experimental results demonstrate that our approach consistently yields high-fidelity surface reconstruction from normals observed at varying distances, outperforming existing multi-view normal integration methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_20337 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representation Yang, Tongyu Guo, Heng Matsushita, Yasuyuki Okura, Fumio Luo, Yu Fan, Xin Computer Vision and Pattern Recognition Previous multi-view normal integration methods typically sample a single ray per pixel, without considering the spatial area covered by each pixel, which varies with camera intrinsics and the camera-to-object distance. Consequently, when the target object is captured at different distances, the normals at corresponding pixels may differ across views. This multi-view surface normal inconsistency results in the blurring of high-frequency details in the reconstructed surface. To address this issue, we propose a scale-encoded neural surface representation that incorporates the pixel coverage area into the neural representation. By associating each 3D point with a spatial scale and calculating its normal from a hybrid grid-based encoding, our method effectively represents multi-scale surface normals captured at varying distances. Furthermore, to enable scale-aware surface reconstruction, we introduce a mesh extraction module that assigns an optimal local scale to each vertex based on the training observations. Experimental results demonstrate that our approach consistently yields high-fidelity surface reconstruction from normals observed at varying distances, outperforming existing multi-view normal integration methods. |
| title | High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.20337 |