English

Automated Reconstruction of 3D Open Surfaces from Sparse Point Clouds

Computer Vision and Pattern Recognition 2023-01-20 v2 Graphics

Abstract

Real-world 3D data may contain intricate details defined by salient surface gaps. Automated reconstruction of these open surfaces (e.g., non-watertight meshes) is a challenging problem for environment synthesis in mixed reality applications. Current learning-based implicit techniques can achieve high fidelity on closed-surface reconstruction. However, their dependence on the distinction between the inside and outside of a surface makes them incapable of reconstructing open surfaces. Recently, a new class of implicit functions have shown promise in reconstructing open surfaces by regressing an unsigned distance field. Yet, these methods rely on a discretized representation of the raw data, which loses important surface details and can lead to outliers in the reconstruction. We propose IPVNet, a learning-based implicit model that predicts the unsigned distance between a surface and a query point in 3D space by leveraging both raw point cloud data and its discretized voxel counterpart. Experiments on synthetic and real-world public datasets demonstrates that IPVNet outperforms the state of the art while producing far fewer outliers in the reconstruction.

Keywords

Cite

@article{arxiv.2210.15059,
  title  = {Automated Reconstruction of 3D Open Surfaces from Sparse Point Clouds},
  author = {Mohammad Samiul Arshad and William J. Beksi},
  journal= {arXiv preprint arXiv:2210.15059},
  year   = {2023}
}

Comments

To be presented at the 2022 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) Workshop on Photorealistic Image and Environment Synthesis for Mixed Reality (PIES-MR)

R2 v1 2026-06-28T04:36:19.639Z