Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors

by   Baorui Ma, et al.

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.


page 1

page 2

page 3

page 4

page 7

page 8

page 9

page 10


Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping

Learning signed distance functions (SDFs) from 3D point clouds is an imp...

Surface Reconstruction from Point Clouds by Learning Predictive Context Priors

Surface reconstruction from point clouds is vital for 3D computer vision...

Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds

Surface reconstruction for point clouds is an important task in 3D compu...

Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priors

It is vital to infer signed distance functions (SDFs) from 3D point clou...

Pointersect: Neural Rendering with Cloud-Ray Intersection

We propose a novel method that renders point clouds as if they are surfa...

Learning Occupancy Function from Point Clouds for Surface Reconstruction

Implicit function based surface reconstruction has been studied for a lo...

Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces

Reconstructing continuous surfaces from 3D point clouds is a fundamental...

Please sign up or login with your details

Forgot password? Click here to reset