DCHM: Depth-Consistent Human Modeling for Multiview Detection

TL;DR

DCHM introduces a novel depth-consistent human modeling framework that enhances multiview pedestrian detection accuracy by producing precise, noise-reduced 3D human representations without relying on human-labeled annotations.

Contribution

The paper presents DCHM, a new method for multiview human modeling that achieves depth consistency and accurate pedestrian localization in complex scenarios without human annotations.

Findings

Reduces noise in human modeling compared to previous methods.

Outperforms state-of-the-art baselines in multiview pedestrian detection.

First to reconstruct pedestrians and perform multiview segmentation in challenging environments.

Abstract

Multiview pedestrian detection typically involves two stages: human modeling and pedestrian localization. Human modeling represents pedestrians in 3D space by fusing multiview information, making its quality crucial for detection accuracy. However, existing methods often introduce noise and have low precision. While some approaches reduce noise by fitting on costly multiview 3D annotations, they often struggle to generalize across diverse scenes. To eliminate reliance on human-labeled annotations and accurately model humans, we propose Depth-Consistent Human Modeling (DCHM), a framework designed for consistent depth estimation and multiview fusion in global coordinates. Specifically, our proposed pipeline with superpixel-wise Gaussian Splatting achieves multiview depth consistency in sparse-view, large-scaled, and crowded scenarios, producing precise point clouds for pedestrian localization. Extensive validations demonstrate that our method significantly reduces noise during human modeling, outperforming previous state-of-the-art baselines. Additionally, to our knowledge, DCHM is the first to reconstruct pedestrians and perform multiview segmentation in such a challenging setting. Code is available on the \href{https://jiahao-ma.github.io/DCHM/}{project page}.