Partial Person Re-identification with Alignment and Hallucination

TL;DR

This paper introduces Partial Matching Net (PMN), a novel approach for partial person re-identification that detects body joints, aligns views, hallucinates missing parts, and improves matching accuracy in CCTV scenarios.

Contribution

The paper presents a new neural network architecture that combines alignment and hallucination for partial person re-identification, addressing challenges of misalignment and missing body parts.

Findings

Significant improvement over existing methods on three datasets.

Effective body joint detection and view alignment in partial images.

Successful hallucination of missing body parts enhances matching accuracy.

Abstract

Partial person re-identification involves matching pedestrian frames where only a part of a body is visible in corresponding images. This reflects practical CCTV surveillance scenario, where full person views are often not available. Missing body parts make the comparison very challenging due to significant misalignment and varying scale of the views. We propose Partial Matching Net (PMN) that detects body joints, aligns partial views and hallucinates the missing parts based on the information present in the frame and a learned model of a person. The aligned and reconstructed views are then combined into a joint representation and used for matching images. We evaluate our approach and compare to other methods on three different datasets, demonstrating significant improvements.