Recovering Fine Details for Neural Implicit Surface Reconstruction

TL;DR

D-NeuS is a novel neural implicit surface reconstruction method that enhances fine detail recovery by introducing new loss functions, improving accuracy and outperforming existing approaches in multi-view 3D reconstruction.

Contribution

We propose D-NeuS, which extends NeuS with two loss functions to better recover fine geometric details in neural implicit surface reconstruction.

Findings

Achieves higher accuracy in surface reconstruction.

Recovers finer geometric details than previous methods.

Outperforms state-of-the-art techniques in experiments.

Abstract

Recent works on implicit neural representations have made significant strides. Learning implicit neural surfaces using volume rendering has gained popularity in multi-view reconstruction without 3D supervision. However, accurately recovering fine details is still challenging, due to the underlying ambiguity of geometry and appearance representation. In this paper, we present D-NeuS, a volume rendering-base neural implicit surface reconstruction method capable to recover fine geometry details, which extends NeuS by two additional loss functions targeting enhanced reconstruction quality. First, we encourage the rendered surface points from alpha compositing to have zero signed distance values, alleviating the geometry bias arising from transforming SDF to density for volume rendering. Second, we impose multi-view feature consistency on the surface points, derived by interpolating SDF zero-crossings from sampled points along rays. Extensive quantitative and qualitative results demonstrate that our method reconstructs high-accuracy surfaces with details, and outperforms the state of the art.