Pose-Normalized Image Generation for Person Re-identification

By Xuelin Qian, Yanwei Fu, Tao A. Xiang, Wenxuan Wang, Jie Qiu, Yang Wu, Yu-Gang Jiang, Xiangyang Xue. European Conference on Computer Vision, 2017

475 citations recorded by the source corpus.

Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired training data and learning discriminative identity-sensitive and view-invariant features in the presence of large pose variations. In this work, we address both problems by proposing a novel deep person image generation model for synthesizing realistic person images conditional on the pose. The model is based on a generative adversarial network (GAN) designed specifically for pose normalization in re-id, thus termed pose-normalization GAN (PN-GAN). With the synthesized images, we can learn a new type of deep re-id feature free of the influence of pose variations. We show that this feature is strong on its own and complementary to features learned with the original images. Importantly, under the transfer learning setting, we show that our model generalizes well to any new re-id dataset without the need for collecting any training data for model fine-tuning. The model thus has the potential to make re-id model truly scalable.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/66e4f5e354240a022789353798ce92e4ab68e109

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

Citations in the corpus

A Strong Baseline and Batch Normalization Neck for Deep Person Re-Identification (2019, unknown): “5 PN-GAN [32] 9 89.”
Learning Discriminative Features with Multiple Granularities for Person Re-Identification (2018, background): “Just during recent months, some deep Re-ID methods [3, 40, 34, 26] have achieved breakthrough with high-level identification rates and mean average precision.”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, background): “A pose-normalized image generation approach is designed in [115], which enhances the robustness against pose variations.”
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification (2019, background): “Most of the existing work is categorized in two ways as follows: pose transfer [18, 22, 6] and style transfer [32, 19, 5, 31].”
OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields (2018, methodology): “A growing number of computer vision and machine learning applications require 2D human pose estimation as an input for their systems [56], [57], [58], [59], [60], [61], [62].”
Pose-Invariant Embedding for Deep Person Re-Identification (2017, unknown): “of various poses [31]–[33].”
Applications of Generative Adversarial Networks (GANs): An Updated Review (2019, background): “Qian et al. [91] proposed a pose-normalization GAN model (PN-GAN) for alleviating the impact of pose variation.”
A Survey on Generative Adversarial Networks: Variants, Applications, and Training (2020, background): “v2Pix [141], GAN-Fit [142], Deforming Autoencoders (DAE) [143], Dual Variational Generator (DVG) [144] and 3D Aided Duet GAN (3D-AD-GAN) [145] for face image generation; Pose Normalized GAN (PN- GAN) [146] and Identity Preserving GAN (IP-GAN) [147] for person re-identification; and Deep Convolutiona”
Joint Discriminative and Generative Learning for Person Re-Identification (2019, methodology): “Instead of using a single supervision as in almost all previous meth-ods [17,31,56], we treat the generated images in two different perspectives through the primary feature learning and ﬁne-grained feature mining, where the former focuses on the structure-invariant clothing information and the…”