High-Quality Textured 3D Shape Reconstruction with Cascaded Fully Convolutional Networks
Lists
Only you see this
Abstract
We present a learning-based approach to reconstructing high-resolution three-dimensional (3D) shapes with detailed geometry and high-fidelity textures. Albeit extensively studied, algorithms for 3D reconstruction from multi-view depth-and-color (RGB-D) scans are still prone to measurement noise and occlusions; limited scanning or capturing angles also often lead to incomplete reconstructions. Propelled by recent advances in 3D deep learning techniques, in this paper, we introduce a novel computation- and memory-efficient cascaded 3D convolutional network architecture, which learns to reconstruct implicit surface representations as well as the corresponding color information from noisy and imperfect RGB-D maps. The proposed 3D neural network performs reconstruction in a progressive and coarse-to-fine manner, achieving unprecedented output resolution and fidelity. Meanwhile, an algorithm for end-to-end training of the proposed cascaded structure is developed. We further introduce Human10, a newly created dataset containing both detailed and textured full-body reconstructions as well as corresponding raw RGB-D scans of 10 subjects. Qualitative and quantitative experimental results on both synthetic and real-world datasets demonstrate that the presented approach outperforms existing state-of-the-art work regarding visual quality and accuracy of reconstructed models.
BibTeX
@article{liu2021high,
author = {Zheng-Ning Liu and Yan‐Pei Cao and Zhengfei Kuang and Leif Kobbelt and Shi‐Min Hu},
title = {{High-Quality Textured 3D Shape Reconstruction with Cascaded Fully Convolutional Networks}},
journal = {IEEE Trans. Vis. Comput. Graph.},
year = {2021},
url = {https://openreview.net/forum?id=UI9GdO2fgI},
}Loading related content...