# Multi-View Crowd Counting With Self-Supervised Learning

arXiv: https://arxiv.org/abs/2509.21918 · HTML: https://mlsanity.com/paper/2509.21918/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 11 of 11)

- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [Neural Unsigned Distance Fields for Implicit Function Learning](https://mlsanity.com/paper/2010.13938/) (2020)
- [SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos](https://mlsanity.com/paper/2308.09244/) (2023)
- [Cross View Fusion for 3D Human Pose Estimation](https://mlsanity.com/paper/1909.01203/) (2019)
- [Cross-View Cross-Scene Multi-View Crowd Counting](https://mlsanity.com/paper/2205.01551/) (2022)
- [Wide-Area Crowd Counting: Multi-View Fusion Networks for Counting in Large Scenes](https://mlsanity.com/paper/2012.00946/) (2020)
- [CountFormer: Multi-View Crowd Counting Transformer](https://mlsanity.com/paper/2407.02047/) (2024)
- [3D Crowd Counting via Geometric Attention-guided Multi-View Fusion](https://mlsanity.com/paper/2003.08162/) (2020)

## Abstract (arXiv)

Multi-view counting (MVC) methods have attracted significant research attention and stimulated remarkable progress in recent years. Despite their success, most MVC methods have focused on improving performance by following the fully supervised learning (FSL) paradigm, which often requires large amounts of annotated data. In this work, we propose SSLCounter, a novel self-supervised learning (SSL) framework for MVC that leverages neural volumetric rendering to alleviate the reliance on large-scale annotated datasets. SSLCounter learns an implicit representation w.r.t. the scene, enabling the reconstruction of continuous geometry shape and the complex, view-dependent appearance of their 2D projections via differential neural rendering. Owing to its inherent flexibility, the key idea of our method can be seamlessly integrated into exsiting frameworks. Notably, extensive experiments demonstrate that SSLCounter not only demonstrates state-of-the-art performances but also delivers competitive performance with only using 70% proportion of training data, showcasing its superior data efficiency across multiple MVC benchmarks.