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

Matiur Rahman Minar¹

Thai Thanh Tuan¹

Heejune Ahn¹

Paul Rosin²

Yu-Kun Lai²

¹Seoul National University of Science and Technology

²Cardiff University

CVPRW 2020 3rd Workshop on Computer Vision for Fashion, Art and Design

[workshop]

[pdf]

[code|Model|Data]

[video]

[slide]

[bibtex]

We proposed CP-VTON+, a new pipeline for fully image-based virtual try-on (VTON) for fashion clothing, solving the limitations of state-of-the-art VTON approaches.

Recently proposed Image-based virtual try-on (VTON) approaches have several challenges regarding diverse human poses and cloth styles. First, clothing warping networks often generate highly distorted and misaligned warped clothes, due to the erroneous clothing-agnostic 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 human representation and improper training loss for compositionmask generation. We propose CP-VTON+ (Clothing shape and texture Preserving VTON) to overcome these issues, which significantly outperforms the state-of-the-art methods, both quantitatively and qualitatively.

Video

Results

Citation


							
							Matiur Rahman Minar, Thai Thanh Tuan, Heejune Ahn, Paul Rosin, and Yu-Kun Lai. "CP-VTON+: Clothing Shape and Texture Preserving Image-Based Virtual Try-On." In: CVPR Workshop on Computer Vision for Fashion, Art and Design (CVPRW), 2020.
					
							


							
							@InProceedings{Minar_CPP_2020_CVPR_Workshops,
							
							
   	title={CP-VTON+: Clothing Shape and Texture Preserving Image-Based Virtual Try-On},
							
   	author={Minar, Matiur Rahman and Thai Thanh Tuan and Ahn, Heejune and Rosin, Paul and Lai, Yu-Kun},
							
   	booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
							
   	month = {June},
							
   	year={2020}
							
}

Acknowledgements

This webpage template was borrowed from Articulation-aware CSM, who borrowed it from some colorful folks.