Progressive Pose Attention Transfer for Person Image Generation

By Zhen Zhu, Tengteng Huang, Baoguang Shi, Miao Yu, Bofei Wang, Xiang Bai. Computer Vision and Pattern Recognition, 2019

356 citations recorded by the source corpus.

This paper proposes a new generative adversarial network to the problem of pose transfer, i.e., transferring the pose of a given person to a target one. The generator of the network comprises a sequence of Pose-Attentional Transfer Blocks that each transfers certain regions it attends to, generating the person image progressively. Compared with those in previous works, our generated person images possess better appearance consistency and shape consistency with the input images, thus significantly more realistic-looking. The efficacy and efficiency of the proposed network are validated both qualitatively and quantitatively on Market-1501 and DeepFashion. Furthermore, the proposed architecture can generate training images for person re-identification, alleviating data insufficiency.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/576dd6fd076114b86c108f5364e7f0f2aed21ad7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Oron Ashual
2. Oran Gafni
3. Changick Kim
4. Taekyung Kim
5. Yisroel Mirsky
6. Wenke Lee
7. Jian Zhao
8. Seokeon Choi

Citations in the corpus

• Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification (2019, methodology): “Existing ReID methods mainly treat visible images captured by single-modality cameras, and depend on human appearance for RGB-RGB matching [35, 42, 45, 25, 36, 26].”
• Thin-Plate Spline Motion Model for Image Animation (2022, methodology): “However, these approaches, which rely on labeled data, only work for specific objects, such as faces [9, 11, 30, 35] and human bodies [6, 18, 23, 27, 37].”
• The Creation and Detection of Deepfakes (2020, methodology): “To ensure that patterns, shapes, and textures are mapped realistically between frames, the authors of [169] developed a GAN which uses novel Pose-Attentional Transfer blocks (PATB) inside the generator.”
• Single-Shot Freestyle Dance Reenactment (2020, background): “In still images, the problem of pose transfer is well studied [28, 37, 1, 45, 9, 57, 11, 10, 39, 30, 26], out of which [9, 39, 30] use a human parser, as we do.”
• Semantically Multi-Modal Image Synthesis (2020, unknown): “…synthesis applications, such as image-to-image translation [21, 19, 43, 57, 29, 31, 17], super resolution [28, 22], domain adaption [16, 54], single model image synthesis [56, 39, 35, 40], style transfer [18, 7, 22], person image generation [33, 59, 13] and image synthesis from text [50, 51] etc .”