PSDiff: Diffusion Model for Person Search With Iterative and Collaborative Refinement
Jia, Chengyou Luo, Minnan Dang, Zhuohang Dai, Guang Chang, Xiaojun Wang, Jingdong
Jia, Chengyou
Luo, Minnan
Dang, Zhuohang
Dai, Guang
Chang, Xiaojun
Wang, Jingdong
Supervisor
Department
Computer Vision
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Dominant Person Search methods aim to localize and recognize query persons in a unified network, which jointly optimizes the two sub-tasks of pedestrian detection and Re-Identification (ReID). Despite significant progress, current methods face two primary challenges: 1) the pedestrian candidates learned within detectors are suboptimal for the ReID task. 2) the potential for collaboration between two sub-tasks is overlooked. To address 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. Distinct from the conventional Detection-to-ReID approach, our denoising paradigm discards prior pedestrian candidates generated by detectors, thereby avoiding the local optimum problem 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.
Citation
C. Jia, M. Luo, Z. Dang, G. Dai, X. Chang and J. Wang, "PSDiff: Diffusion Model for Person Search With Iterative and Collaborative Refinement," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 35, no. 6, pp. 5153-5165, June 2025
Source
IEEE Transactions on Circuits and Systems for Video Technology
Conference
Keywords
Person search, diffusion model, person re-identification, object detection
Subjects
Source
Publisher
IEEE