Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Clouds

TL;DR

This paper introduces a novel implicit filtering method that enhances neural signed distance functions from point clouds, improving geometric detail preservation and surface smoothness in 3D shape reconstruction.

Contribution

The paper proposes a non-linear implicit filter that smooths the SDF while maintaining high-frequency details, extending filtering to non-zero level sets for better regularization.

Findings

Improved surface reconstruction quality over state-of-the-art methods.

Enhanced preservation of geometric details like edges and corners.

Better regularization of the zero level set in SDFs.

Abstract

Neural signed distance functions (SDFs) have shown powerful ability in fitting the shape geometry. However, inferring continuous signed distance fields from discrete unoriented point clouds still remains a challenge. The neural network typically fits the shape with a rough surface and omits fine-grained geometric details such as shape edges and corners. In this paper, we propose a novel non-linear implicit filter to smooth the implicit field while preserving high-frequency geometry details. Our novelty lies in that we can filter the surface (zero level set) by the neighbor input points with gradients of the signed distance field. By moving the input raw point clouds along the gradient, our proposed implicit filtering can be extended to non-zero level sets to keep the promise consistency between different level sets, which consequently results in a better regularization of the zero level set. We conduct comprehensive experiments in surface reconstruction from objects and complex scene point clouds, the numerical and visual comparisons demonstrate our improvements over the state-of-the-art methods under the widely used benchmarks.