@article{Xu2025, 
author = {Jiamin Xu and Zihan Zhu and Hujun Bao and Weiwei Xu},
title = {Hybrid mesh-neural representation for 3D transparent object reconstruction},
year = {2025},
journal = {Computational Visual Media},
volume = {11},
number = {1},
pages = {123-140},
keywords = {transparent object, 3D reconstruction, environment matting, neural rendering},
url = {https://www.sciopen.com/article/10.26599/CVM.2025.9450328},
doi = {10.26599/CVM.2025.9450328},
abstract = {In this study, we propose a novel method to reconstruct the 3D shapes of transparent objects using images captured by handheld cameras under natural lighting conditions. It combines the advantages of an explicit mesh and multi-layer perceptron (MLP) network as a hybrid representation to simplify the capture settings used in recent studies. After obtaining an initial shape through multi-view silhouettes, we introduced surface-based local MLPs to encode the vertex displacement field (VDF) for reconstructing surface details. The design of local MLPs allowed representation of the VDF in a piecewise manner using two-layer MLP networks to support the optimization algorithm. Defining local MLPs on the surface instead of on the volume also reduced the search space. Such a hybrid representation enabled us to relax the ray–pixel correspondences that represent the light path constraint to our designed ray–cell correspondences, which significantly simplified the implementation of a single-image-based environment-matting algorithm. We evaluated our representation and reconstruction algorithm on several transparent objects based on ground truth models. The experimental results show that our method produces high-quality reconstructions that are superior to those of state-of-the-art methods using a simplified data-acquisition setup.}
}