# Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identification

arXiv: https://arxiv.org/abs/2304.07883 · HTML: https://mlsanity.com/paper/2304.07883/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 65 references that are in the map.
- First posted on arXiv 16 Apr 2023.

## Builds on (most cited first, 30 of 42)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects](https://mlsanity.com/paper/1809.10790/) (2018)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Meta-Sim: Learning to Generate Synthetic Datasets](https://mlsanity.com/paper/1904.11621/) (2019)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [Synthetic Data for Deep Learning](https://mlsanity.com/paper/1909.11512/) (2019)
- [Modeling Visual Context is Key to Augmenting Object Detection Datasets](https://mlsanity.com/paper/1807.07428/) (2018)
- [T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks](https://mlsanity.com/paper/1808.01454/) (2018)
- [MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?](https://mlsanity.com/paper/2108.09518/) (2021)
- [SIFT Meets CNN: A Decade Survey of Instance Retrieval](https://mlsanity.com/paper/1608.01807/) (2016)
- [Instance-level Image Retrieval using Reranking Transformers](https://mlsanity.com/paper/2103.12236/) (2021)
- [GiT: Graph Interactive Transformer for Vehicle Re-identification](https://mlsanity.com/paper/2107.05475/) (2021)
- [AAformer: Auto-Aligned Transformer for Person Re-Identification](https://mlsanity.com/paper/2104.00921/) (2021)
- [HAT: Hierarchical Aggregation Transformers for Person Re-identification](https://mlsanity.com/paper/2107.05946/) (2021)
- [A survey of advances in vision-based vehicle re-identification](https://mlsanity.com/paper/1905.13258/) (2019)
- [An Empirical Study of Multi-Task Learning on BERT for Biomedical Text Mining](https://mlsanity.com/paper/2005.02799/) (2020)
- [TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification](https://mlsanity.com/paper/2105.14432/) (2021)
- [Procedural Generation of Videos to Train Deep Action Recognition Networks](https://mlsanity.com/paper/1612.00881/) (2016)
- [PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data](https://mlsanity.com/paper/2005.00673/) (2020)
- [Deformation-Aware 3D Model Embedding and Retrieval](https://mlsanity.com/paper/2004.01228/) (2020)

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

- [Addressing the Depth-of-Field Constraint: A New Paradigm for High Resolution Multi-Focus Image Fusion](https://mlsanity.com/paper/2510.19581/) (2025)

## Abstract (arXiv)

Instance-level object re-identification is a fundamental computer vision task, with applications from image retrieval to intelligent monitoring and fraud detection. In this work, we propose the novel task of damaged object re-identification, which aims at distinguishing changes in visual appearance due to deformations or missing parts from subtle intra-class variations. To explore this task, we leverage the power of computer-generated imagery to create, in a semi-automatic fashion, high-quality synthetic images of the same bike before and after a damage occurs. The resulting dataset, Bent & Broken Bicycles (BBBicycles), contains 39,200 images and 2,800 unique bike instances spanning 20 different bike models. As a baseline for this task, we propose TransReI3D, a multi-task, transformer-based deep network unifying damage detection (framed as a multi-label classification task) with object re-identification. The BBBicycles dataset is available at https://huggingface.co/datasets/GrainsPolito/BBBicycles