Ryota Natsume, Shunsuke Saito, Zeng Huang, Weikai Chen, Chongyang Ma, Hao Li, Shigeo Morishima
SiCloPe: Silhouette-Based Clothed People
CoRR abs/1901.00049 (2019)
CVPR 2019 Best Paper Award Finalist
We introduce a new silhouette-based representation for modeling clothed human bodies using deep generative models. Our method can reconstruct a complete and textured 3D model of a person wearing clothes from a single input picture gmwin4 다운로드. Inspired by the visual hull algorithm, our implicit representation uses 2D silhouettes and 3D joints of a body pose to describe the immense shape complexity and variations of clothed people pencil 다운로드. Given a segmented 2D silhouette of a person and its inferred 3D joints from the input picture, we first synthesize consistent silhouettes from novel view points around the subject Internet explorer 11 offline. The synthesized silhouettes, which are the most consistent with the input segmentation are fed into a deep visual hull algorithm for robust 3D shape prediction Download tracetcp. We then infer the texture of the subject’s back view using the frontal image and segmentation mask as input to a conditional generative adversarial network Download the Intel Graphics Control Panel. Our experiments demonstrate that our silhouette-based model is an effective representation and the appearance of the back view can be predicted reliably using an image-to-image translation network 신문명조체. While classic methods based on parametric models often fail for single-view images of subjects with challenging clothing, our approach can still produce successful results, which are comparable to those obtained from multi-view input High definition download of Zootopia.