Work

High‐Fidelity Multi‐View Normal Integration With Scale‐Encoded Neural Surface Representation

Year: 2026

Type: article

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 (SNSR) 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.

Source: Computer Graphics Forum

DOI: 10.1111/cgf.70427

Authors: Tongyu Yang, Heng Guo, Yasuyuki Matsushita, Fumio Okura, Yu Luo, Xin Fan

Institutions: Dalian University of Technology, Beijing University of Posts and Telecommunications, The University of Osaka

Language: English

Topic: 3D Shape Modeling and Analysis

Subfield: Computational Mechanics

Field: Engineering

Domain: Physical Sciences

Open Access status: green

Funders: National Natural Science Foundation of China, China Scholarship Council, Key Research and Development Program of Liaoning Province