Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation
This work addresses the need for detailed human shape estimation from images, which is important for applications like virtual reality and animation, but it appears incremental as it builds on existing parametric models with refinements.
The paper tackles the problem of estimating detailed human body shapes from a single image, which is challenging due to variations in shape, pose, and viewpoint. It proposes a hierarchical mesh deformation framework that outperforms previous state-of-the-art methods, achieving better accuracy in 2D IoU and 3D metric distance.
This paper presents a novel framework to recover detailed human body shapes from a single image. It is a challenging task due to factors such as variations in human shapes, body poses, and viewpoints. Prior methods typically attempt to recover the human body shape using a parametric based template that lacks the surface details. As such the resulting body shape appears to be without clothing. In this paper, we propose a novel learning-based framework that combines the robustness of parametric model with the flexibility of free-form 3D deformation. We use the deep neural networks to refine the 3D shape in a Hierarchical Mesh Deformation (HMD) framework, utilizing the constraints from body joints, silhouettes, and per-pixel shading information. We are able to restore detailed human body shapes beyond skinned models. Experiments demonstrate that our method has outperformed previous state-of-the-art approaches, achieving better accuracy in terms of both 2D IoU number and 3D metric distance. The code is available in https://github.com/zhuhao-nju/hmd.git