Inner-Body Dataset

In this paper, we propose the first method to allow everyone to easily reconstruct their own 3D inner-body under clothing from a self-captured video with the mean reconstruction error of 0.73cm within 15s, avoiding privacy concerns arising from nudity or minimal clothing. To alleviate the complexity and uncertainty of directly estimating 3D inner-bodies under clothing, we propose a novel two-stage framework with a Semantic-guided Undressing Network (SUNet) to learn semantically related body features and an Intra-Inter Transformer Network (IITNet) to reconstruct 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 the dataset will be provided for research purposes.