Papers › CCUP: A Controllable Synthetic Data Generation Pipeline for Pretraining Cloth-Changing...

CCUP: A Controllable Synthetic Data Generation Pipeline for Pretraining Cloth-Changing Person Re-Identification Models

17 Oct 2024arXiv:2410.13567archive 2025-07-28

Yujian Zhao, Chengru Wu, Yinong Xu, Xuanzheng Du, Ruiyu Li, Guanglin Niu

Cloth-changing person re-identification (CC-ReID), also known as Long-Term Person Re-Identification (LT-ReID) is a critical and challenging research topic in computer vision that has recently garnered significant attention. However, due to the high cost of constructing CC-ReID data, the existing data-driven models are hard to train efficiently on limited data, causing overfitting issue. To address this challenge, we propose a low-cost and efficient pipeline for generating controllable and high-quality synthetic data simulating the surveillance of real scenarios specific to the CC-ReID task. Particularly, we construct a new self-annotated CC-ReID dataset named Cloth-Changing Unreal Person (CCUP), containing 6,000 IDs, 1,179,976 images, 100 cameras, and 26.5 outfits per individual. Based on this large-scale dataset, we introduce an effective and scalable pretrain-finetune framework for enhancing the generalization capabilities of the traditional CC-ReID models. The extensive experiments demonstrate that two typical models namely TransReID and FIRe^2, when integrated into our framework, outperform other state-of-the-art models after pretraining on CCUP and finetuning on the benchmarks such as PRCC, VC-Clothes and NKUP. The CCUP is available at: https://github.com/yjzhao1019/CCUP.

PaperPDFCode

Code

yjzhao1019/ccup officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Cloth-Changing Person Re-IdentificationPerson Re-IdentificationSynthetic Data Generation

Datasets

Introduced by this paper, per the archive.

CCUP

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification PRCC TransReid+CCUP Rank-1 58.9 #9 of 13 Archive leaderboard report
Person Re-Identification PRCC TransReid+CCUP mAP 59.0 #9 of 13 Archive leaderboard report
Person Re-Identification VC-Clothes Transreid+CCUP Rank-1 83.3 #3 of 6 Archive leaderboard report
Person Re-Identification VC-Clothes Transreid+CCUP mAP 83.1 #3 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections