Fine-detailed Neural Indoor Scene Reconstruction using multi-level importance sampling and multi-view consistency
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_ | 1866916431726116864 |
|---|---|
| author | Li, Xinghui Ji, Yuchen Lai, Xiansong Zhang, Wanting |
| author_facet | Li, Xinghui Ji, Yuchen Lai, Xiansong Zhang, Wanting |
| contents | Recently, neural implicit 3D reconstruction in indoor scenarios has become popular due to its simplicity and impressive performance. Previous works could produce complete results leveraging monocular priors of normal or depth. However, they may suffer from over-smoothed reconstructions and long-time optimization due to unbiased sampling and inaccurate monocular priors. In this paper, we propose a novel neural implicit surface reconstruction method, named FD-NeuS, to learn fine-detailed 3D models using multi-level importance sampling strategy and multi-view consistency methodology. Specifically, we leverage segmentation priors to guide region-based ray sampling, and use piecewise exponential functions as weights to pilot 3D points sampling along the rays, ensuring more attention on important regions. In addition, we introduce multi-view feature consistency and multi-view normal consistency as supervision and uncertainty respectively, which further improve the reconstruction of details. Extensive quantitative and qualitative results show that FD-NeuS outperforms existing methods in various scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07597 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fine-detailed Neural Indoor Scene Reconstruction using multi-level importance sampling and multi-view consistency Li, Xinghui Ji, Yuchen Lai, Xiansong Zhang, Wanting Computer Vision and Pattern Recognition Recently, neural implicit 3D reconstruction in indoor scenarios has become popular due to its simplicity and impressive performance. Previous works could produce complete results leveraging monocular priors of normal or depth. However, they may suffer from over-smoothed reconstructions and long-time optimization due to unbiased sampling and inaccurate monocular priors. In this paper, we propose a novel neural implicit surface reconstruction method, named FD-NeuS, to learn fine-detailed 3D models using multi-level importance sampling strategy and multi-view consistency methodology. Specifically, we leverage segmentation priors to guide region-based ray sampling, and use piecewise exponential functions as weights to pilot 3D points sampling along the rays, ensuring more attention on important regions. In addition, we introduce multi-view feature consistency and multi-view normal consistency as supervision and uncertainty respectively, which further improve the reconstruction of details. Extensive quantitative and qualitative results show that FD-NeuS outperforms existing methods in various scenes. |
| title | Fine-detailed Neural Indoor Scene Reconstruction using multi-level importance sampling and multi-view consistency |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.07597 |