This paper presents a neural network to estimate a detailed depth map of the foreground human in a single RGB image. The result captures geometry details such as cloth wrinkles, which are important in visualization applications. To achieve this goal, we separate the depth map into a smooth base shape and a residual detail shape and design a network with two branches to regress them respectively. We design a training strategy to ensure both base and detail shapes can be faithfully learned by the corresponding network branches. Furthermore, we introduce a novel network layer to fuse a rough depth map and surface normals to further improve the final result. Quantitative comparison with fused `ground truth' captured by real depth cameras and qualitative examples on unconstrained Internet images demonstrate the strength of the proposed method. The code is available at https://github.com/sfu-gruvi-3dv/deep_human.
@article{arxiv.1910.01275,
title = {A Neural Network for Detailed Human Depth Estimation from a Single Image},
author = {Sicong Tang and Feitong Tan and Kelvin Cheng and Zhaoyang Li and Siyu Zhu and Ping Tan},
journal= {arXiv preprint arXiv:1910.01275},
year = {2019}
}