PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement

Chengyou Jia, Minnan Luo, Zhuohang Dang, Guang Dai, Xiaojun Chang, Jingdong Wang, Qinghua Zheng

Abstract

Dominant Person Search methods aim to localize and recognize query persons in a unified network, which jointly optimizes two sub-tasks, \ie, detection and Re-IDentification (ReID). Despite significant progress, two major challenges remain: 1) Detection-prior modules in previous methods are suboptimal for the ReID task. 2) The collaboration between two sub-tasks is ignored. To alleviate these issues, we present a novel Person Search framework based on the Diffusion model, PSDiff. PSDiff formulates the person search as a dual denoising process from noisy boxes and ReID embeddings to ground truths. Unlike existing methods that follow the Detection-to-ReID paradigm, our denoising paradigm eliminates detection-prior modules to avoid the local-optimum of the ReID task. Following the new paradigm, we further design a new Collaborative Denoising Layer (CDL) to optimize detection and ReID sub-tasks in an iterative and collaborative way, which makes two sub-tasks mutually beneficial. Extensive experiments on the standard benchmarks show that PSDiff achieves state-of-the-art performance with fewer parameters and elastic computing overhead.
BibTeX
@article{jia2025psdiff,
  author = {Chengyou Jia and Minnan Luo and Zhuohang Dang and Guang Dai and Xiaojun Chang and Jingdong Wang and Qinghua Zheng},
  title = {{PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement}},
  journal = {IEEE Trans. Circuits Syst. Video Technol.},
  year = {2025},
  doi = {10.1109/tcsvt.2024.3524733},
}
Figure