Edge-aware Neural Implicit Surface Reconstruction

Xinghui Li, Yikang Ding, Jia Guo, Xiansong Lai, Shihao Ren, Wensen Feng, Long ZengICME 2023 · OpenReview

Abstract

Recently, neural implicit 3D reconstruction in indoor scenarios has achieved impressive performance. Utilizing the volume rendering method and neural implicit representation to learn 3D scenes, such per-scene optimization methods could reconstruct pretty complete models but also suffer from missing details and overly-smoothed reconstructions. In this paper, we propose a novel edge-aware neural implicit surface reconstruction method, named Ea-NeuS, to learn high-quality 3D models with fine details. Specifically, we use the edge of objects to locate the important areas, and propose a simple yet effective edge-guided ray-sampling strategy to learn the 3D models. The aforementioned edge information further guides the normal prior supervision, which helps reduce inaccurate optimization in detailed regions. We additionally use the visibility-aware sparse points to pilot the 3D points sampling along the rays and perform explicit supervision. As a result, our method achieves superior performance compared with existing methods on various scenes.
BibTeX
@inproceedings{li2023edge,
  author = {Xinghui Li and Yikang Ding and Jia Guo and Xiansong Lai and Shihao Ren and Wensen Feng and Long Zeng},
  title = {{Edge-aware Neural Implicit Surface Reconstruction}},
  booktitle = {ICME},
  year = {2023},
  url = {https://openreview.net/forum?id=pwfCCNCvt0},
}

Loading related content...

Figure