A Neural Network for Detailed Human Depth Estimation from a Single Image
This work addresses the need for high-fidelity human depth estimation in visualization applications, representing an incremental advancement in the field.
The paper tackles the problem of estimating detailed depth maps of foreground humans from single RGB images, achieving results that capture fine geometry details like cloth wrinkles, with quantitative comparisons showing improvements over existing methods.
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.