Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors
This addresses a limitation in 3D reconstruction for real-world applications where point clouds are often sparse, offering improved performance in domains like computer vision and robotics.
The paper tackles the problem of reconstructing surfaces from sparse 3D point clouds, which current methods struggle with due to density requirements, and achieves state-of-the-art accuracy by using an on-surface prior to learn Signed Distance Functions without ground truth data.
It is an important task to reconstruct surfaces from 3D point clouds. Current methods are able to reconstruct surfaces by learning Signed Distance Functions (SDFs) from single point clouds without ground truth signed distances or point normals. However, they require the point clouds to be dense, which dramatically limits their performance in real applications. To resolve this issue, we propose to reconstruct highly accurate surfaces from sparse point clouds with an on-surface prior. We train a neural network to learn SDFs via projecting queries onto the surface represented by the sparse point cloud. Our key idea is to infer signed distances by pushing both the query projections to be on the surface and the projection distance to be the minimum. To achieve this, we train a neural network to capture the on-surface prior to determine whether a point is on a sparse point cloud or not, and then leverage it as a differentiable function to learn SDFs from unseen sparse point cloud. Our method can learn SDFs from a single sparse point cloud without ground truth signed distances or point normals. Our numerical evaluation under widely used benchmarks demonstrates that our method achieves state-of-the-art reconstruction accuracy, especially for sparse point clouds.