# CountFormer: Multi-View Crowd Counting Transformer arXiv: https://arxiv.org/abs/2407.02047 ยท HTML: https://mlsanity.com/paper/2407.02047/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Builds on 71 of its 100 references that are in the map. - First posted on arXiv 2 Jul 2024. ## Builds on (most cited first, 30 of 71) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021) - [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016) - [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019) - [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020) - [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019) - [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015) - [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022) - [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020) - [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022) - [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021) - [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016) - [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019) - [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022) - [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022) - [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023) - [BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework](https://mlsanity.com/paper/2205.13790/) (2022) - [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023) - [MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2208.14437/) (2022) - [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022) - [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023) - [NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection](https://mlsanity.com/paper/1904.07392/) (2019) - [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018) - [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://mlsanity.com/paper/2205.02833/) (2022) - [FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras](https://mlsanity.com/paper/2104.10490/) (2021) - [CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers](https://mlsanity.com/paper/2207.02202/) (2022) - [OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception](https://mlsanity.com/paper/2303.03991/) (2023) - [Scene as Occupancy](https://mlsanity.com/paper/2306.02851/) (2023) - [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019) ## Built on by (most cited first, 12 of 12) - [Semi-Supervised Multi-View Crowd Counting by Ranking Multi-View Fusion Models](https://mlsanity.com/paper/2512.16243/) (2025) - [Embodied Crowd Counting](https://mlsanity.com/paper/2503.08367/) (2025) - [Consistent-Point: Consistent Pseudo-Points for Semi-Supervised Crowd Counting and Localization](https://mlsanity.com/paper/2503.12441/) (2025) - [Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization](https://mlsanity.com/paper/2510.19330/) (2025) - [Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods](https://mlsanity.com/paper/2601.12500/) (2026) - [Crowd Detection Using Very-Fine-Resolution Satellite Imagery](https://mlsanity.com/paper/2504.19546/) (2025) - [Active View Selection for Scene-level Multi-view Crowd Counting and Localization with Limited Labeling Budget](https://mlsanity.com/paper/2509.16684/) (2025) - [Multi-View Crowd Counting With Self-Supervised Learning](https://mlsanity.com/paper/2509.21918/) (2025) - [TP-MVCC: Tri-plane Multi-view Fusion Model for Silkie Chicken Counting](https://mlsanity.com/paper/2509.24329/) (2025) - [SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization](https://mlsanity.com/paper/2603.23956/) (2026) - [Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting](https://mlsanity.com/paper/2603.24106/) (2026) - [Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes](https://mlsanity.com/paper/2604.19318/) (2026) ## Abstract (arXiv) Multi-view counting (MVC) methods have shown their superiority over single-view counterparts, particularly in situations characterized by heavy occlusion and severe perspective distortions. However, hand-crafted heuristic features and identical camera layout requirements in conventional MVC methods limit their applicability and scalability in real-world scenarios.In this work, we propose a concise 3D MVC framework called CountFormerto elevate multi-view image-level features to a scene-level volume representation and estimate the 3D density map based on the volume features. By incorporating a camera encoding strategy, CountFormer successfully embeds camera parameters into the volume query and image-level features, enabling it to handle various camera layouts with significant differences.Furthermore, we introduce a feature lifting module capitalized on the attention mechanism to transform image-level features into a 3D volume representation for each camera view. Subsequently, the multi-view volume aggregation module attentively aggregates various multi-view volumes to create a comprehensive scene-level volume representation, allowing CountFormer to handle images captured by arbitrary dynamic camera layouts. The proposed method performs favorably against the state-of-the-art approaches across various widely used datasets, demonstrating its greater suitability for real-world deployment compared to conventional MVC frameworks.