Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

article · 2020

Controllable Person Image Synthesis With Attribute-Decomposed GAN

Yifang Men, Yiming Mao, Yuning Jiang, Wei‐Ying Ma, Zhouhui Lian

Cited by 259Abstract and details only

Abstract

This paper introduces the Attribute-Decomposed GAN, a novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes (e.g., pose, head, upper clothes and pants) provided in various source inputs. The core idea of the proposed model is to embed human attributes into the latent space as independent codes and thus achieve flexible and continuous control of attributes via mixing and interpolation operations in explicit style representations. Specifically, a new architecture consisting of two encoding pathways with style block connections is proposed to decompose the original hard mapping into multiple more accessible subtasks. In source pathway, we further extract component layouts with an off-the-shelf human parser and feed them into a shared global texture encoder for decomposed latent codes. This strategy allows for the synthesis of more realistic output images and automatic separation of un-annotated attributes. Experimental results demonstrate the proposed method's superiority over the state of the art in pose transfer and its effectiveness in the brand-new task of component attribute transfer.

Cite this paper

APA 7

Men, Y., Mao, Y., Jiang, Y., Ma, W., & Lian, Z. (2020). Controllable Person Image Synthesis With Attribute-Decomposed GAN. https://doi.org/10.1109/cvpr42600.2020.00513

MLA 9

Men, Yifang, et al. “Controllable Person Image Synthesis With Attribute-Decomposed GAN.” 2020, pp. 5083–92, https://doi.org/10.1109/cvpr42600.2020.00513.

Chicago

Men, Yifang, Yiming Mao, Yuning Jiang, Wei‐Ying Ma, and Zhouhui Lian. 2020. “Controllable Person Image Synthesis With Attribute-Decomposed GAN.” https://doi.org/10.1109/cvpr42600.2020.00513.

Harvard

Men, Y. et al. (2020) ‘Controllable Person Image Synthesis With Attribute-Decomposed GAN’. Available at: https://doi.org/10.1109/cvpr42600.2020.00513.

BibTeX
@article{men2020controllable,
  title = {{Controllable Person Image Synthesis With Attribute-Decomposed GAN}},
  author = {Men, Yifang and Mao, Yiming and Jiang, Yuning and Ma, Wei‐Ying and Lian, Zhouhui},
  pages = {5083--5092},
  year = {2020},
  doi = {10.1109/cvpr42600.2020.00513}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.

Related papers