DiGS : Divergence guided shape implicit neural representation for unoriented point clouds

TL;DR

This paper introduces DiGS, a divergence-guided shape representation method for unoriented point clouds that improves surface reconstruction without needing normal vectors, using a novel divergence constraint and geometric initialization.

Contribution

The paper presents a divergence-guided learning approach for shape implicit representations that does not require normal vectors and introduces a new geometric initialization for sinusoidal INRs.

Findings

Achieves state-of-the-art performance on surface reconstruction tasks.

Effectively orients gradients to match unknown normals without ground truth normals.

Improves convergence with a novel geometric initialization.

Abstract

Shape implicit neural representations (INRs) have recently shown to be effective in shape analysis and reconstruction tasks. Existing INRs require point coordinates to learn the implicit level sets of the shape. When a normal vector is available for each point, a higher fidelity representation can be learned, however normal vectors are often not provided as raw data. Furthermore, the method's initialization has been shown to play a crucial role for surface reconstruction. In this paper, we propose a divergence guided shape representation learning approach that does not require normal vectors as input. We show that incorporating a soft constraint on the divergence of the distance function favours smooth solutions that reliably orients gradients to match the unknown normal at each point, in some cases even better than approaches that use ground truth normal vectors directly. Additionally, we introduce a novel geometric initialization method for sinusoidal INRs that further improves convergence to the desired solution. We evaluate the effectiveness of our approach on the task of surface reconstruction and shape space learning and show SOTA performance compared to other unoriented methods. Code and model parameters available at our project page https://chumbyte.github.io/DiGS-Site/.