Learning to Infer Inner-Body Under Clothing From Monocular Video

IEEE Trans Vis Comput Graph. 2022 Aug 29;PP. doi: 10.1109/TVCG.2022.3202240. Online ahead of print.


Accurately estimating the human inner-body under clothing is very important for body measurement, virtual try-on and VR/AR applications. In this paper, we propose the first method to allow everyone to easily reconstruct their own 3D inner-body under daily clothing from a self-captured video with the mean reconstruction error of 0.73 cm within 15 s. This avoids privacy concerns arising from nudity or minimal clothing. Specifically, we propose a novel two-stage framework with a Semantic-guided Undressing Network (SUNet) and an Intra-Inter Transformer Network (IITNet). SUNet learns semantically related body features to alleviate the complexity and uncertainty of directly estimating 3D inner-bodies under clothing. IITNet reconstructs the 3D inner-body model by making full use of intra-frame and inter-frame information, which addresses the misalignment of inconsistent poses in different frames. Experimental results on both public datasets and our collected dataset demonstrate the effectiveness of the proposed method. The code and dataset is available for research purposes at http://cic.tju.edu.cn/faculty/likun/projects/Inner-Body.