Partial-REID Partially Occluded Person Re-Identification Dataset

The Partial-REID dataset is a uniquely designed partially occluded person re-identification dataset. It uses a new method called Deep Spatial Reconstruction (DSR) for partially occluded person re-identification. It can flexibly process portraits of any size without image alignment and solve the problem of partially occluded person re-identification.

Example image:

The dataset includes 600 images of 60 people, each with 5 full-body images and 5 occluded images. The images are collected by 6 cameras on a university campus from different perspectives, backgrounds, and different types of occlusions.