# Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification

arXiv: https://arxiv.org/abs/1701.03153 · HTML: https://mlsanity.com/paper/1701.03153/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jan 2017.

## Built on by (most cited first, 20 of 20)

- [A Comprehensive Survey on Data Augmentation](https://mlsanity.com/paper/2405.09591/) (2024)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Synthetic Data in Human Analysis: A Survey](https://mlsanity.com/paper/2208.09191/) (2022)
- [Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification](https://mlsanity.com/paper/2109.10498/) (2021)
- [Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification](https://mlsanity.com/paper/2204.02611/) (2022)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Human Image Generation: A Comprehensive Survey](https://mlsanity.com/paper/2212.08896/) (2022)
- [SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation](https://mlsanity.com/paper/2108.00249/) (2021)
- [Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic](https://mlsanity.com/paper/2310.04416/) (2023)
- [An Open-World, Diverse, Cross-Spatial-Temporal Benchmark for Dynamic Wild Person Re-Identification](https://mlsanity.com/paper/2403.15119/) (2024)
- [Enhancing and Dissecting Crowd Counting By Synthetic Data](https://mlsanity.com/paper/2201.08992/) (2022)
- [Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification](https://mlsanity.com/paper/2109.05542/) (2021)
- [TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification](https://mlsanity.com/paper/2112.14239/) (2021)
- [Finer-Personalization Rank: Fine-Grained Retrieval Examines Identity Preservation for Personalized Generation](https://mlsanity.com/paper/2512.19026/) (2025)
- [SynPlay: Large-Scale Synthetic Human Data with Real-World Diversity for Aerial-View Perception](https://mlsanity.com/paper/2408.11814/) (2024)
- [An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval](https://mlsanity.com/paper/2503.22171/) (2025)
- [Is Synthetic Dataset Reliable for Benchmarking Generalizable Person Re-Identification?](https://mlsanity.com/paper/2209.05047/) (2022)
- [A Masked Face Classification Benchmark on Low-Resolution Surveillance Images](https://mlsanity.com/paper/2211.13061/) (2022)
- [Illumination Variation Correction Using Image Synthesis For Unsupervised Domain Adaptive Person Re-Identification](https://mlsanity.com/paper/2301.09702/) (2023)
- [A Dual-stage Prompt-driven Privacy-preserving Paradigm for Person Re-Identification](https://mlsanity.com/paper/2511.05092/) (2025)

## Abstract (arXiv)

Re-identification is generally carried out by encoding the appearance of a subject in terms of outfit, suggesting scenarios where people do not change their attire. In this paper we overcome this restriction, by proposing a framework based on a deep convolutional neural network, SOMAnet, that additionally models other discriminative aspects, namely, structural attributes of the human figure (e.g. height, obesity, gender). Our method is unique in many respects. First, SOMAnet is based on the Inception architecture, departing from the usual siamese framework. This spares expensive data preparation (pairing images across cameras) and allows the understanding of what the network learned. Second, and most notably, the training data consists of a synthetic 100K instance dataset, SOMAset, created by photorealistic human body generation software. Synthetic data represents a good compromise between realistic imagery, usually not required in re-identification since surveillance cameras capture low-resolution silhouettes, and complete control of the samples, which is useful in order to customize the data w.r.t. the surveillance scenario at-hand, e.g. ethnicity. SOMAnet, trained on SOMAset and fine-tuned on recent re-identification benchmarks, outperforms all competitors, matching subjects even with different apparel. The combination of synthetic data with Inception architectures opens up new research avenues in re-identification.