# Two-level Data Augmentation for Calibrated Multi-view Detection

arXiv: https://arxiv.org/abs/2210.10756 · HTML: https://mlsanity.com/paper/2210.10756/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 19 Oct 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Generalization in Deep Learning](https://mlsanity.com/paper/1710.05468/) (2017)
- [Learning Data Augmentation Strategies for Object Detection](https://mlsanity.com/paper/1906.11172/) (2019)
- [Dataset Augmentation in Feature Space](https://mlsanity.com/paper/1702.05538/) (2017)
- [Multiview Detection with Feature Perspective Transformation](https://mlsanity.com/paper/2007.07247/) (2020)
- [MVDepthNet: Real-time Multiview Depth Estimation Neural Network](https://mlsanity.com/paper/1807.08563/) (2018)
- [Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)](https://mlsanity.com/paper/2108.05888/) (2021)
- [Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection](https://mlsanity.com/paper/1704.05775/) (2017)
- [Deep Multi-camera People Detection](https://mlsanity.com/paper/1702.04593/) (2017)
- [The WILDTRACK Multi-Camera Person Dataset](https://mlsanity.com/paper/1707.09299/) (2017)

## Built on by (most cited first, 13 of 13)

- [Unsupervised Multi-view Pedestrian Detection](https://mlsanity.com/paper/2305.12457/) (2023)
- [Enhanced Multi-View Pedestrian Detection Using Probabilistic Occupancy Volume](https://mlsanity.com/paper/2503.10982/) (2025)
- [MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost](https://mlsanity.com/paper/2509.01157/) (2025)
- [MVUDA: Unsupervised Domain Adaptation for Multi-view Pedestrian Detection](https://mlsanity.com/paper/2412.04117/) (2024)
- [One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking](https://mlsanity.com/paper/2507.08494/) (2025)
- [Toward unlabeled multi-view 3D pedestrian detection by generalizable AI: techniques and performance analysis](https://mlsanity.com/paper/2308.04515/) (2023)
- [MSMVD: Exploiting Multi-scale Image Features via Multi-scale BEV Features for Multi-view Pedestrian Detection](https://mlsanity.com/paper/2508.20447/) (2025)
- [3DRot: Rediscovering the Missing Primitive for RGB-Based 3D Augmentation](https://mlsanity.com/paper/2508.01423/) (2025)
- [CAD-Free Learning of Spacecraft Pose Estimators via NeRF-Based Augmentations](https://mlsanity.com/paper/2605.19649/) (2026)
- [Fully Distributed Multi-View 3D Tracking in Real-Time](https://mlsanity.com/paper/2606.13127/) (2026)
- [MVDGC: Joint 3D and 2D Multi-view Pedestrian Detection via Dual Geometric Constraints](https://mlsanity.com/paper/2607.00273/) (2026)
- [MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model](https://mlsanity.com/paper/2608.20639/) (2026)
- [Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Tracking](https://mlsanity.com/paper/2608.24130/) (2026)

## Abstract (arXiv)

Data augmentation has proven its usefulness to improve model generalization and performance. While it is commonly applied in computer vision application when it comes to multi-view systems, it is rarely used. Indeed geometric data augmentation can break the alignment among views. This is problematic since multi-view data tend to be scarce and it is expensive to annotate. In this work we propose to solve this issue by introducing a new multi-view data augmentation pipeline that preserves alignment among views. Additionally to traditional augmentation of the input image we also propose a second level of augmentation applied directly at the scene level. When combined with our simple multi-view detection model, our two-level augmentation pipeline outperforms all existing baselines by a significant margin on the two main multi-view multi-person detection datasets WILDTRACK and MultiviewX.