CP-VTON+: Clothing Shape and Texture Preserving Image-Based Virtual Try-On

Recently proposed Image-based virtual try-on (VTON) approaches have several challenges regarding diverse human poses and clothing styles. First, clothing warping networks often generate highly distorted and misaligned warped clothes, due to the erroneous clothingagnostic human representations, mismatches in input images for clothing-human matching, and improper regularization transform parameters. Second, blending networks can fail to retain the remaining clothes due to the wrong representation of humans and improper training loss for the composition-mask generation. We propose CP-VTON+ (Clothing shape and texture Preserving VTON) to overcome these issues, which significantly outperforms the state-ofthe-art methods, both quantitatively and qualitatively.