deep-person-reid and ReID-Survey
Torchreid is a practical deep learning framework for implementing person re-identification models, while the ReID-Survey is a comprehensive review paper documenting the research landscape—making them complementary resources where the survey provides theoretical context and the framework enables practical implementation of surveyed methods.
About deep-person-reid
KaiyangZhou/deep-person-reid
Torchreid: Deep learning person re-identification in PyTorch.
Supports both image and video re-identification modalities with multi-dataset training and cross-dataset evaluation under standardized protocols. Built on omni-scale feature learning architectures (OSNet) with exportable models to ONNX, OpenVINO, and TFLite for deployment. Includes advanced techniques like domain generalization, instance normalization, and mixing strategies (MixStyle) for improving generalization across datasets and camera views.
About ReID-Survey
mangye16/ReID-Survey
Deep Learning for Person Re-identification: A Survey and Outlook
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work