# Multiview Detection with Feature Perspective Transformation

arXiv: https://arxiv.org/abs/2007.07247 · HTML: https://mlsanity.com/paper/2007.07247/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jul 2020.

## Built on by (most cited first, 30 of 71)

- [Vision-Centric BEV Perception: A Survey](https://mlsanity.com/paper/2208.02797/) (2022)
- [Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)](https://mlsanity.com/paper/2108.05888/) (2021)
- [EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View](https://mlsanity.com/paper/2310.13350/) (2023)
- [MMPTRACK: Large-scale Densely Annotated Multi-camera Multiple People Tracking Benchmark](https://mlsanity.com/paper/2111.15157/) (2021)
- [Lifting Multi-View Detection and Tracking to the Bird's Eye View](https://mlsanity.com/paper/2403.12573/) (2024)
- [ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking](https://mlsanity.com/paper/2308.13229/) (2023)
- [Aerial Monocular 3D Object Detection](https://mlsanity.com/paper/2208.03974/) (2022)
- [3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization](https://mlsanity.com/paper/2207.10895/) (2022)
- [Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2501.04670/) (2025)
- [Self-Supervised Visibility Learning for Novel View Synthesis](https://mlsanity.com/paper/2103.15407/) (2021)
- [Generalizable Multi-Camera 3D Pedestrian Detection](https://mlsanity.com/paper/2104.05813/) (2021)
- [Two-level Data Augmentation for Calibrated Multi-view Detection](https://mlsanity.com/paper/2210.10756/) (2022)
- [Task-Oriented Communication for Edge Video Analytics](https://mlsanity.com/paper/2211.14049/) (2022)
- [Bringing Generalization to Deep Multi-View Pedestrian Detection](https://mlsanity.com/paper/2109.12227/) (2021)
- [Multi-view Tracking Using Weakly Supervised Human Motion Prediction](https://mlsanity.com/paper/2210.10771/) (2022)
- [Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond](https://mlsanity.com/paper/2202.14034/) (2022)
- [Unsupervised Multi-view Pedestrian Detection](https://mlsanity.com/paper/2305.12457/) (2023)
- [Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking](https://mlsanity.com/paper/2405.18606/) (2024)
- [Voxelized 3D Feature Aggregation for Multiview Detection](https://mlsanity.com/paper/2112.03471/) (2021)
- [Enhanced Multi-View Pedestrian Detection Using Probabilistic Occupancy Volume](https://mlsanity.com/paper/2503.10982/) (2025)
- [Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention](https://mlsanity.com/paper/2208.09211/) (2022)
- [From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration](https://mlsanity.com/paper/2212.09298/) (2022)
- [DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception](https://mlsanity.com/paper/2401.08687/) (2024)
- [Multi-View People Detection in Large Scenes via Supervised View-Wise Contribution Weighting](https://mlsanity.com/paper/2405.19943/) (2024)
- [Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic Dataset](https://mlsanity.com/paper/2412.13569/) (2024)
- [MITracker: Multi-View Integration for Visual Object Tracking](https://mlsanity.com/paper/2502.20111/) (2025)
- [DCHM: Depth-Consistent Human Modeling for Multiview Detection](https://mlsanity.com/paper/2507.14505/) (2025)
- [MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost](https://mlsanity.com/paper/2509.01157/) (2025)
- [Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic](https://mlsanity.com/paper/2310.04416/) (2023)
- [MVM3Det: A Novel Method for Multi-view Monocular 3D Detection](https://mlsanity.com/paper/2109.10473/) (2021)

## Abstract (arXiv)

Incorporating multiple camera views for detection alleviates the impact of occlusions in crowded scenes. In a multiview system, we need to answer two important questions when dealing with ambiguities that arise from occlusions. First, how should we aggregate cues from the multiple views? Second, how should we aggregate unreliable 2D and 3D spatial information that has been tainted by occlusions? To address these questions, we propose a novel multiview detection system, MVDet. For multiview aggregation, existing methods combine anchor box features from the image plane, which potentially limits performance due to inaccurate anchor box shapes and sizes. In contrast, we take an anchor-free approach to aggregate multiview information by projecting feature maps onto the ground plane (bird's eye view). To resolve any remaining spatial ambiguity, we apply large kernel convolutions on the ground plane feature map and infer locations from detection peaks. Our entire model is end-to-end learnable and achieves 88.2% MODA on the standard Wildtrack dataset, outperforming the state-of-the-art by 14.1%. We also provide detailed analysis of MVDet on a newly introduced synthetic dataset, MultiviewX, which allows us to control the level of occlusion. Code and MultiviewX dataset are available at https://github.com/hou-yz/MVDet.