# Diffusion-based Synthetic Data Generation for Visible-Infrared Person Re-Identification

arXiv: https://arxiv.org/abs/2503.12472 · HTML: https://mlsanity.com/paper/2503.12472/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 39 references that are in the map.
- First posted on arXiv 16 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2108.02938/) (2021)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Is synthetic data from generative models ready for image recognition?](https://mlsanity.com/paper/2210.07574/) (2022)
- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2007.09314/) (2020)
- [RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment](https://mlsanity.com/paper/1910.05839/) (2019)
- [BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations](https://mlsanity.com/paper/2201.04684/) (2022)
- [Neural Feature Search for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2104.02366/) (2021)
- [Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model](https://mlsanity.com/paper/2403.19600/) (2024)

## Built on by (most cited first, 10 of 10)

- [NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-Identification](https://mlsanity.com/paper/2505.20001/) (2025)
- [BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2603.14243/) (2026)
- [POCI-Diff: 3D-Layout Guided Diffusion for Controllable Synthetic Surveillance Data Generation](https://mlsanity.com/paper/2601.14056/) (2026)
- [OmniPerson: Unified Identity-Preserving Pedestrian Generation](https://mlsanity.com/paper/2512.02554/) (2025)
- [CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification](https://mlsanity.com/paper/2604.02808/) (2026)
- [Find Them All: Unveiling MLLMs for Versatile Person Re-identification](https://mlsanity.com/paper/2508.06908/) (2025)
- [UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation](https://mlsanity.com/paper/2605.14626/) (2026)
- [DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion](https://mlsanity.com/paper/2606.00153/) (2026)
- [Dual-Edged Homogeneous-Modality Similarity: Towards Visible-Infrared Modality-Incomplete Person Re-Identification with Modality Adaptive Matching](https://mlsanity.com/paper/2607.18688/) (2026)
- [Dual-Space Modality Consistency Learning for Universal Cross-Modal Re-Identification](https://mlsanity.com/paper/2608.06943/) (2026)

## Abstract (arXiv)

The performance of models is intricately linked to the abundance of training data. In Visible-Infrared person Re-IDentification (VI-ReID) tasks, collecting and annotating large-scale images of each individual under various cameras and modalities is tedious, time-expensive, costly and must comply with data protection laws, posing a severe challenge in meeting dataset requirements. Current research investigates the generation of synthetic data as an efficient and privacy-ensuring alternative to collecting real data in the field. However, a specific data synthesis technique tailored for VI-ReID models has yet to be explored. In this paper, we present a novel data generation framework, dubbed Diffusion-based VI-ReID data Expansion (DiVE), that automatically obtain massive RGB-IR paired images with identity preserving by decoupling identity and modality to improve the performance of VI-ReID models. Specifically, identity representation is acquired from a set of samples sharing the same ID, whereas the modality of images is learned by fine-tuning the Stable Diffusion (SD) on modality-specific data. DiVE extend the text-driven image synthesis to identity-preserving RGB-IR multimodal image synthesis. This approach significantly reduces data collection and annotation costs by directly incorporating synthetic data into ReID model training. Experiments have demonstrated that VI-ReID models trained on synthetic data produced by DiVE consistently exhibit notable enhancements. In particular, the state-of-the-art method, CAJ, trained with synthetic images, achieves an improvement of about 9% in mAP over the baseline on the LLCM dataset. Code: https://github.com/BorgDiven/DiVE