From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $α$-NeuS
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917896346664960 |
|---|---|
| author | Zhang, Haoran Deng, Junkai Chen, Xuhui Hou, Fei Wang, Wencheng Qin, Hong Qian, Chen He, Ying |
| author_facet | Zhang, Haoran Deng, Junkai Chen, Xuhui Hou, Fei Wang, Wencheng Qin, Hong Qian, Chen He, Ying |
| contents | Traditional 3D shape reconstruction techniques from multi-view images, such as structure from motion and multi-view stereo, face challenges in reconstructing transparent objects. Recent advances in neural radiance fields and its variants primarily address opaque or transparent objects, encountering difficulties to reconstruct both transparent and opaque objects simultaneously. This paper introduces $α$-Neus -- an extension of NeuS -- that proves NeuS is unbiased for materials from fully transparent to fully opaque. We find that transparent and opaque surfaces align with the non-negative local minima and the zero iso-surface, respectively, in the learned distance field of NeuS. Traditional iso-surfacing extraction algorithms, such as marching cubes, which rely on fixed iso-values, are ill-suited for such data. We develop a method to extract the transparent and opaque surface simultaneously based on DCUDF. To validate our approach, we construct a benchmark that includes both real-world and synthetic scenes, demonstrating its practical utility and effectiveness. Our data and code are publicly available at https://github.com/728388808/alpha-NeuS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_05362 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $α$-NeuS Zhang, Haoran Deng, Junkai Chen, Xuhui Hou, Fei Wang, Wencheng Qin, Hong Qian, Chen He, Ying Computer Vision and Pattern Recognition Traditional 3D shape reconstruction techniques from multi-view images, such as structure from motion and multi-view stereo, face challenges in reconstructing transparent objects. Recent advances in neural radiance fields and its variants primarily address opaque or transparent objects, encountering difficulties to reconstruct both transparent and opaque objects simultaneously. This paper introduces $α$-Neus -- an extension of NeuS -- that proves NeuS is unbiased for materials from fully transparent to fully opaque. We find that transparent and opaque surfaces align with the non-negative local minima and the zero iso-surface, respectively, in the learned distance field of NeuS. Traditional iso-surfacing extraction algorithms, such as marching cubes, which rely on fixed iso-values, are ill-suited for such data. We develop a method to extract the transparent and opaque surface simultaneously based on DCUDF. To validate our approach, we construct a benchmark that includes both real-world and synthetic scenes, demonstrating its practical utility and effectiveness. Our data and code are publicly available at https://github.com/728388808/alpha-NeuS. |
| title | From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $α$-NeuS |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.05362 |