Pose-Normalized Image Generation for Person Re-identification
This work addresses scalability and data scarcity in person re-identification, offering a potential solution for real-world applications, though it is incremental as it builds on existing GAN-based methods.
The paper tackles the challenges of limited cross-view training data and pose variations in person re-identification by proposing a pose-normalization GAN (PN-GAN) to generate realistic person images conditioned on pose, enabling the learning of discriminative, view-invariant features that are strong on their own and complementary to original features, with demonstrated generalization to new datasets without fine-tuning.
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.