# MSMVD: Exploiting Multi-scale Image Features via Multi-scale BEV Features for Multi-view Pedestrian Detection

arXiv: https://arxiv.org/abs/2508.20447 · HTML: https://mlsanity.com/paper/2508.20447/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [CityPersons: A Diverse Dataset for Pedestrian Detection](https://mlsanity.com/paper/1702.05693/) (2017)
- [SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes](https://mlsanity.com/paper/2304.05170/) (2023)
- [Multiview Detection with Feature Perspective Transformation](https://mlsanity.com/paper/2007.07247/) (2020)
- [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)
- [YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection](https://mlsanity.com/paper/2308.05480/) (2023)
- [3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization](https://mlsanity.com/paper/2207.10895/) (2022)
- [Two-level Data Augmentation for Calibrated Multi-view Detection](https://mlsanity.com/paper/2210.10756/) (2022)
- [Bringing Generalization to Deep Multi-View Pedestrian Detection](https://mlsanity.com/paper/2109.12227/) (2021)
- [Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection](https://mlsanity.com/paper/1904.02948/) (2019)
- [Mahalanobis Distance-based Multi-view Optimal Transport for Multi-view Crowd Localization](https://mlsanity.com/paper/2409.01726/) (2024)
- [F2DNet: Fast Focal Detection Network for Pedestrian Detection](https://mlsanity.com/paper/2203.02331/) (2022)
- [Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention](https://mlsanity.com/paper/2208.09211/) (2022)
- [Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic Dataset](https://mlsanity.com/paper/2412.13569/) (2024)

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

- [MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model](https://mlsanity.com/paper/2608.20639/) (2026)

## Abstract (arXiv)

Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view (BEV) from multi-view images. In MVPD, end-to-end trainable deep learning methods have progressed greatly. However, they often struggle to detect pedestrians with consistently small or large scales in views or with vastly different scales between views. This is because they do not exploit multi-scale image features to generate the BEV feature and detect pedestrians. To overcome this problem, we propose a novel MVPD method, called Multi-Scale Multi-View Detection (MSMVD). MSMVD generates multi-scale BEV features by projecting multi-scale image features extracted from individual views into the BEV space, scale-by-scale. Each of these BEV features inherits the properties of its corresponding scale image features from multiple views. Therefore, these BEV features help the precise detection of pedestrians with consistently small or large scales in views. Then, MSMVD combines information at different scales of multiple views by processing the multi-scale BEV features using a feature pyramid network. This improves the detection of pedestrians with vastly different scales between views. Extensive experiments demonstrate that exploiting multi-scale image features via multi-scale BEV features greatly improves the detection performance, and MSMVD outperforms the previous highest MODA by 4.5 points on the GMVD dataset.