High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representation

TL;DR

This paper introduces a scale-encoded neural surface representation that accounts for pixel coverage area, enabling high-fidelity multi-view surface reconstruction from normals captured at varying distances.

Contribution

It proposes a novel scale-encoded neural surface model and a mesh extraction method for improved multi-view normal integration across different object distances.

Findings

Outperforms existing methods in surface reconstruction quality.

Effectively handles multi-scale surface normals from varying distances.

Produces detailed and accurate 3D reconstructions.

Abstract

Previous multi-view normal integration methods typically sample a single ray per pixel, without considering the spatial area covered by each pixel, which varies with camera intrinsics and the camera-to-object distance. Consequently, when the target object is captured at different distances, the normals at corresponding pixels may differ across views. This multi-view surface normal inconsistency results in the blurring of high-frequency details in the reconstructed surface. To address this issue, we propose a scale-encoded neural surface representation that incorporates the pixel coverage area into the neural representation. By associating each 3D point with a spatial scale and calculating its normal from a hybrid grid-based encoding, our method effectively represents multi-scale surface normals captured at varying distances. Furthermore, to enable scale-aware surface reconstruction, we introduce a mesh extraction module that assigns an optimal local scale to each vertex based on the training observations. Experimental results demonstrate that our approach consistently yields high-fidelity surface reconstruction from normals observed at varying distances, outperforming existing multi-view normal integration methods.