Significance of Anatomical Constraints in Virtual Try-On

Significance of Anatomical Constraints in Virtual Try-On

1TCG CREST, Kolkata, India
2Osaka University, Osaka, Japan
3Indian Statistical Institute, Kolkata, India
4Indian Institute of Information Technology Kalyani, India
Accepted in IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI), Dec, 2023

This paper mainly contributes two things, (1) We propose a part-based solution approach that addresses the overlap issues by warping the independently movable parts separately. (2) We propose ATAG transform, a geometric warping approach that can tackle clothing warpings related to complex arm bendings.

Abstract


The system of Virtual Try-ON (VTON) allows a user to try a product virtually. In general, a VTON system takes a clothing source and a person's image to predict the try-on output of the person in the given clothing. Although existing methods perform well for simple poses, in case of bent or crossed arms posture or when there is a significant difference between the alignment of the source clothing and the pose of the target person, these methods fail by generating inaccurate clothing deformations. In the VTON methods that employ Thin Plate Spline (TPS) based clothing transformations, this mainly occurs for two reasons - (1)~the second-order smoothness constraint of TPS that restricts the bending of the object plane. (2)~Overlaps among different clothing parts (e.g., sleeves and torso) can not be modeled by a single TPS transformation, as it assumes the clothing as a single planar object; therefore, disregards the independence of movement of different clothing parts. To this end, we make two major contributions. Concerning the bending limitations of TPS, we propose a human AnaTomy-Aware Geometric (ATAG) transformation. Regarding the overlap issue, we propose a part-based warping approach that divides the clothing into independently warpable parts to warp them separately and later combine them. Extensive analysis shows the efficacy of this approach.

Results


VITON-HD dataset


Comparative Study

MPV dataset


Comparative Study

More results of ours

Citation


Will be updated soon
        

Courtesy : https://sds-complete.github.io/