Attention-Guided Multi-scale Neural Dual Contouring
Loading...
Date
2025
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Reconstructing high-quality meshes from binary voxel data is a fundamental task in computer graphics. However, existing methods struggle with low information density and strong discreteness, making it difficult to capture complex geometry and long-range boundary features, often leading to jagged surfaces and loss of sharp details.We propose an Attention-Guided Multiscale Neural Dual Contouring (AGNDC) method to address this challenge. AGNDC refines surface reconstruction through a multi-scale framework, using a hybrid feature extractor that combines global attention and dynamic snake convolution to enhance perception of long-range and high-curvature features. A dynamic feature fusion module aligns multi-scale predictions to improve local detail continuity, while a geometric postprocessing module further refines mesh boundaries and suppresses artifacts. Experiments on the ABC dataset demonstrate the superior performance of AGNDC in both visual and quantitative metrics. It achieves a Chamfer Distance (CD×105) of 9.013 and an F-score of 0.440, significantly reducing jaggedness and improving surface smoothness.
Description
CCS Concepts: Computing methodologies → Mesh generation; Neural networks; Volumetric models
@inproceedings{10.2312:pg.20251291,
booktitle = {Pacific Graphics Conference Papers, Posters, and Demos},
editor = {Christie, Marc and Han, Ping-Hsuan and Lin, Shih-Syun and Pietroni, Nico and Schneider, Teseo and Tsai, Hsin-Ruey and Wang, Yu-Shuen and Zhang, Eugene},
title = {{Attention-Guided Multi-scale Neural Dual Contouring}},
author = {Wu, Fuli and Hu, Chaoran and Li, Wenxuan and Hao, Pengyi},
year = {2025},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {10.2312/pg.20251291}
}