# VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identification

arXiv: https://arxiv.org/abs/2311.16278 · HTML: https://mlsanity.com/paper/2311.16278/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 73 references that are in the map.
- First posted on arXiv 27 Nov 2023.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [Pose Guided Person Image Generation](https://mlsanity.com/paper/1705.09368/) (2017)
- [View Synthesis by Appearance Flow](https://mlsanity.com/paper/1605.03557/) (2016)
- [Deformable GANs for Pose-based Human Image Generation](https://mlsanity.com/paper/1801.00055/) (2017)
- [A Large-Scale Car Dataset for Fine-Grained Categorization and Verification](https://mlsanity.com/paper/1506.08959/) (2015)
- [Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives](https://mlsanity.com/paper/2303.09824/) (2023)
- [Pose-Normalized Image Generation for Person Re-identification](https://mlsanity.com/paper/1712.02225/) (2017)
- [Transformation-Grounded Image Generation Network for Novel 3D View Synthesis](https://mlsanity.com/paper/1703.02921/) (2017)
- [Parsing-based View-aware Embedding Network for Vehicle Re-Identification](https://mlsanity.com/paper/2004.05021/) (2020)
- [Vehicle Re-identification with Viewpoint-aware Metric Learning](https://mlsanity.com/paper/1910.04104/) (2019)
- [VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification](https://mlsanity.com/paper/2004.06305/) (2020)
- [Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather](https://mlsanity.com/paper/2210.15176/) (2022)
- [The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification](https://mlsanity.com/paper/2004.06271/) (2020)
- [A Dual-Path Model With Adaptive Attention For Vehicle Re-Identification](https://mlsanity.com/paper/1905.03397/) (2019)
- [RAM: A Region-Aware Deep Model for Vehicle Re-Identification](https://mlsanity.com/paper/1806.09283/) (2018)
- [Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network](https://mlsanity.com/paper/2008.11423/) (2020)
- [Heterogeneous Relational Complement for Vehicle Re-identification](https://mlsanity.com/paper/2109.07894/) (2021)
- [BoxCars: Improving Fine-Grained Recognition of Vehicles using 3-D Bounding Boxes in Traffic Surveillance](https://mlsanity.com/paper/1703.00686/) (2017)
- [S2R-ViT for Multi-Agent Cooperative Perception: Bridging the Gap from Simulation to Reality](https://mlsanity.com/paper/2307.07935/) (2023)
- [Vehicle Re-identification Using Quadruple Directional Deep Learning Features](https://mlsanity.com/paper/1811.05163/) (2018)
- [Novel Views of Objects from a Single Image](https://mlsanity.com/paper/1602.00328/) (2016)
- [Attributes Guided Feature Learning for Vehicle Re-identification](https://mlsanity.com/paper/1905.08997/) (2019)
- [Deep Transfer Learning for Intelligent Vehicle Perception: a Survey](https://mlsanity.com/paper/2306.15110/) (2023)
- [3D-Assisted Image Feature Synthesis for Novel Views of an Object](https://mlsanity.com/paper/1412.0003/) (2014)
- [Background Segmentation for Vehicle Re-Identification](https://mlsanity.com/paper/1910.06613/) (2019)

## Built on by (most cited first, 1 of 1)

- [3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification](https://mlsanity.com/paper/2604.26520/) (2026)

## Abstract (arXiv)

Vehicle Re-identification (Re-ID) has been broadly studied in the last decade; however, the different camera view angle leading to confused discrimination in the feature subspace for the vehicles of various poses, is still challenging for the Vehicle Re-ID models in the real world. To promote the Vehicle Re-ID models, this paper proposes to synthesize a large number of vehicle images in the target pose, whose idea is to project the vehicles of diverse poses into the unified target pose so as to enhance feature discrimination. Considering that the paired data of the same vehicles in different traffic surveillance cameras might be not available in the real world, we propose the first Pair-flexible Pose Guided Image Synthesis method for Vehicle Re-ID, named as VehicleGAN in this paper, which works for both supervised and unsupervised settings without the knowledge of geometric 3D models. Because of the feature distribution difference between real and synthetic data, simply training a traditional metric learning based Re-ID model with data-level fusion (i.e., data augmentation) is not satisfactory, therefore we propose a new Joint Metric Learning (JML) via effective feature-level fusion from both real and synthetic data. Intensive experimental results on the public VeRi-776 and VehicleID datasets prove the accuracy and effectiveness of our proposed VehicleGAN and JML.