TY - GEN
T1 - High-quality 3D Clothing Reconstruction and Virtual-Try-On
T2 - 2022 International Conference on Multimedia Analysis and Pattern Recognition, MAPR 2022
AU - Tuan, Thai Thanh
AU - Yun, Youngsik
AU - Ahn, Heejune
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Virtual try-on (VTON) is filling the gap between online and offline shopping. This paper extends Cloth3D, which uses top clothing only, and proposes a pipeline for high-resolution virtual try-on for pants based on 3D clothing reconstruction. In-shop pants image is first reconstructed into 3D by finding the SMPL body model fitted to the pants and building the clothing model. Then, the clothing model is reposed to the human reference image and projected to a 2D image to get 3D warped pants. These warped pants and the identities from the reference person image are going through the blending network to get the try-on. Moreover, a target segmentation is also estimated for control input for the blending (in-painting) network. Our experiments and evaluation on a new fashion dataset show natural VTON results for service.
AB - Virtual try-on (VTON) is filling the gap between online and offline shopping. This paper extends Cloth3D, which uses top clothing only, and proposes a pipeline for high-resolution virtual try-on for pants based on 3D clothing reconstruction. In-shop pants image is first reconstructed into 3D by finding the SMPL body model fitted to the pants and building the clothing model. Then, the clothing model is reposed to the human reference image and projected to a 2D image to get 3D warped pants. These warped pants and the identities from the reference person image are going through the blending network to get the try-on. Moreover, a target segmentation is also estimated for control input for the blending (in-painting) network. Our experiments and evaluation on a new fashion dataset show natural VTON results for service.
KW - 3D clothing reconstruction
KW - Depth estimation
KW - In-painting
KW - VTON(Virtual try-on)
KW - conditional Image generation
UR - http://www.scopus.com/inward/record.url?scp=85141936575&partnerID=8YFLogxK
U2 - 10.1109/MAPR56351.2022.9924990
DO - 10.1109/MAPR56351.2022.9924990
M3 - Conference contribution
AN - SCOPUS:85141936575
T3 - 2022 International Conference on Multimedia Analysis and Pattern Recognition, MAPR 2022 - Proceedings
BT - 2022 International Conference on Multimedia Analysis and Pattern Recognition, MAPR 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 13 October 2022 through 14 October 2022
ER -