Abstract
Achieving Clothing Try-On with 2D images is always complicated because retrieving all the characteristics of a person and the clothing can be difficult. The absence of an ideal dataset and the presence of considerable variance in the problem poses challenges. Despite this, there has been a growing interest in this task, thanks to the advancements in generative modelling. Various approaches have been developed and implemented, but due to the data and computation expensive nature of the task, they may not be widely applicable. To overcome this limitation, we present two different models: an Encoder-Decoder-based model and a Generative Adversarial Network-based model, both of which can effectively achieve virtual try-on with minimal architectural complexity through style transfer. Without excessive data, we aim to put the desired garment onto an intended target image. The network has been trained to learn the clothing and posture details of the image and perform the desired style transfer. The proposed method gives competitive results despite a considerable difference in model complexity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Raj A, Sangkloy P, Chang H, Hays J, Ceylan D, Lu J (2018) Swapnet: image based garment transfer. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer vision—ECCV 2018. Springer International Publishing, Cham, pp 679–695
Zheng Z, Yang X, Yu Z, Zheng L, Yang Y, Kautz J (2019) Joint discriminative and generative learning for person re-identification. In: IEEE conference on computer vision and pattern recognition (CVPR)
Gong K, Liang X, Shen X, Lin L (2017) Look into person: self-supervised structure-sensitive learning and a new benchmark for human parsing. CoRR. Available: http://arxiv.org/abs/1703.05446 [Online]
Jetchev N, Bergmann U (2017) The conditional analogy gan: swapping fashion articles on people images
Mo S, Cho M, Shin J (2018) Instagan: instance-aware image-to-image translation. CoRR. Available: http://arxiv.org/abs/1812.10889 [Online]
Pons-Moll G, Pujades S, Hu S, Black M (2017) Clothcap: seamless 4d clothing capture and retargeting. ACM Trans Graph (Proc SIGGRAPH)
Yang S, Amert T, Pan Z, Wang K, Yu L, Berg TL, Lin MC (2016) Detailed garment recovery from a single-view image. CoRR. Available: http://arxiv.org/abs/1608.01250 [Online]
Karras T, Laine S, Aila T (2018) A style-based generator architecture for generative adversarial networks. CoRR. Available: http://arxiv.org/abs/1812.04948 [Online]
Zhang H, Xu T, Li H, Zhang S, Huang X, Wang X, Metaxas DN (2016) Stackgan: text to photo-realistic image synthesis with stacked generative adversarial networks. CoRR. Available: http://arxiv.org/abs/1612.03242 [Online]
Zhu J, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. CoRR. Available: http://arxiv.org/abs/1703.10593 [Online]
Cao Z, Hidalgo Martinez G, Simon T, Wei S, Sheikh YA (2019) Openpose: realtime multi-person 2d pose estimation using part affinity fields. IEEE Trans Patt Anal Machine Intell
Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial networks
Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, Chen X (2016) Improved techniques for training gans
Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2018) Gans trained by a two time-scale update rule converge to a local nash equilibrium
Wang Z, Bovik A, Sheikh H, Simoncelli E (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Sanodiya RK, Mathew J, Saha S, Thalakottur MD (2019) A new transfer learning algorithm in semi-supervised setting. IEEE Access 7:42 956–42 967
Sanodiya RK, Yao L (2020) Unsupervised transfer learning via relative distance comparisons. IEEE Access 8:110 290–110 305
Sanodiya RK, Mathew A, Mathew J, Khushi M (2020) Statistical and geometrical alignment using metric learning in domain adaptation. In: 2020 International joint conference on neural networks (IJCNN). IEEE, pp 1–8
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Karn, R.R.P., Sanodiya, R.K., Chandaluri, E.S., Suryavardan, S., Reddy, L.R., Yao, L. (2022). Virtual Try-On Using Style Transfer. In: Mathew, J., Santhosh Kumar, G., P., D., Jose, J.M. (eds) Responsible Data Science. Lecture Notes in Electrical Engineering, vol 940. Springer, Singapore. https://doi.org/10.1007/978-981-19-4453-6_9
Download citation
DOI: https://doi.org/10.1007/978-981-19-4453-6_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-4452-9
Online ISBN: 978-981-19-4453-6
eBook Packages: Computer ScienceComputer Science (R0)