Point-Query Quadtree for Crowd Counting, Localization, and More

Chengxin Liu, Hao Lu, Zhiguo Cao, Tongliang Liu; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 1676-1685


We show that crowd counting can be viewed as a decomposable point querying process. This formulation enables arbitrary points as input and jointly reasons whether the points are crowd and where they locate. The querying processing, however, raises an underlying problem on the number of necessary querying points. Too few imply underestimation; too many increase computational overhead. To address this dilemma, we introduce a decomposable structure, i.e., the point-query quadtree, and propose a new counting model, termed Point quEry Transformer (PET). PET implements decomposable point querying via data-dependent quadtree splitting, where each querying point could split into four new points when necessary, thus enabling dynamic processing of sparse and dense regions. Such a querying process yields an intuitive, universal modeling of crowd as both the input and output are interpretable and steerable. We demonstrate the applications of PET on a number of crowd-related tasks, including fully-supervised crowd counting and localization, partial annotation learning, and point annotation refinement, and also report state-of-the-art performance. For the first time, we show that a single counting model can address multiple crowd-related tasks across different learning paradigms. Code is available at https://github.com/cxliu0/PET.

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Liu_2023_ICCV, author = {Liu, Chengxin and Lu, Hao and Cao, Zhiguo and Liu, Tongliang}, title = {Point-Query Quadtree for Crowd Counting, Localization, and More}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1676-1685} }