Counting Stacked Objects

TL;DR

This paper introduces a novel 3D counting method that accurately counts stacked objects in multi-view images by combining geometric reconstruction and deep learning, addressing a challenging problem in computer vision.

Contribution

The paper presents a new 3D counting approach that decomposes the task into geometry estimation and occupancy analysis, effectively handling irregularly stacked objects.

Findings

Accurately counts objects in complex stacked arrangements

Works effectively on real-world and synthetic datasets

Provides a publicly available dataset for further research

Abstract

Visual object counting is a fundamental computer vision task underpinning numerous real-world applications, from cell counting in biomedicine to traffic and wildlife monitoring. However, existing methods struggle to handle the challenge of stacked 3D objects in which most objects are hidden by those above them. To address this important yet underexplored problem, we propose a novel 3D counting approach that decomposes the task into two complementary subproblems - estimating the 3D geometry of the object stack and the occupancy ratio from multi-view images. By combining geometric reconstruction and deep learning-based depth analysis, our method can accurately count identical objects within containers, even when they are irregularly stacked. We validate our 3D Counting pipeline on diverse real-world and large-scale synthetic datasets, which we will release publicly to facilitate further research.