Back to Search Start Over

Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification

Authors :
Kim, Inès Hyeonsu
Lee, JoungBin
Son, Soowon
Jin, Woojeong
Cho, Kyusun
Seo, Junyoung
Kwak, Min-Seop
Cho, Seokju
Baek, JeongYeol
Lee, Byeongwon
Kim, Seungryong
Publication Year :
2024

Abstract

Person re-identification (Re-ID) often faces challenges due to variations in human poses and camera viewpoints, which significantly affect the appearance of individuals across images. Existing datasets frequently lack diversity and scalability in these aspects, hindering the generalization of Re-ID models to new camera systems. Previous methods have attempted to address these issues through data augmentation; however, they rely on human poses already present in the training dataset, failing to effectively reduce the human pose bias in the dataset. We propose Diff-ID, a novel data augmentation approach that incorporates sparse and underrepresented human pose and camera viewpoint examples into the training data, addressing the limited diversity in the original training data distribution. Our objective is to augment a training dataset that enables existing Re-ID models to learn features unbiased by human pose and camera viewpoint variations. To achieve this, we leverage the knowledge of pre-trained large-scale diffusion models. Using the SMPL model, we simultaneously capture both the desired human poses and camera viewpoints, enabling realistic human rendering. The depth information provided by the SMPL model indirectly conveys the camera viewpoints. By conditioning the diffusion model on both the human pose and camera viewpoint concurrently through the SMPL model, we generate realistic images with diverse human poses and camera viewpoints. Qualitative results demonstrate the effectiveness of our method in addressing human pose bias and enhancing the generalizability of Re-ID models compared to other data augmentation-based Re-ID approaches. The performance gains achieved by training Re-ID models on our offline augmented dataset highlight the potential of our proposed framework in improving the scalability and generalizability of person Re-ID models.<br />Comment: The project page is available at https://ku-cvlab.github.io/Diff-ID/

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2406.16042
Document Type :
Working Paper