Jing Huang

Jing Huang

PhD Student

Crowd3D: Towards Hundreds of People Reconstruction from a Single Image

Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, 2023

Hao Wen†, Jing Huang†, Huili Cui, Haozhe Lin, Yu-Kun Lai, Lu Fang, Kun Li*
† Equal contribution.

Abstract

Image-based multi-person reconstruction in wide-field large scenes is critical for crowd analysis and security alert. However, existing methods cannot deal with large scenes containing hundreds of people, which encounter the challenges of large number of people, large variations in human scale, and complex spatial distribution.

We propose Crowd3D, the first framework to reconstruct the 3D poses, shapes and locations of hundreds of people with global consistency from a single large-scene image. The core of our approach is to convert the problem of complex crowd localization into pixel localization with the help of our newly defined concept, Human-scene Virtual Interaction Point (HVIP). To reconstruct the crowd with global consistency, we propose a progressive reconstruction network based on HVIP by pre-estimating a scene-level camera and a ground plane. To deal with a large number of persons and various human sizes, we also design an adaptive human-centric cropping scheme. Besides, we contribute a benchmark dataset, LargeCrowd, for crowd reconstruction in a large scene.

Figures

Overview of Crowd3D framework.

Overview of Crowd3D framework.

Citation

@inproceedings{Crowd3D,
  author = {Wen, Hao and Huang, Jing and Cui, Huili and Lin, Haozhe and Lai, Yu-Kun and Fang, Lu and Li, Kun},
  title = {Crowd3D: Towards Hundreds of People Reconstruction from a Single Image},
  booktitle = {CVPR},
  year = {2023},
  pages = {8937--8946}
}