CrowdRec：从单张彩色图像进行3D人群重建
CrowdRec: 3D Crowd Reconstruction from Single Color Images
AI总结：
针对单目图像3D人群重建难题，提出人群约束优化方法，利用现成检测器与单人体网格恢复网络，改进空间分布，实现准确重建。
摘要：
这是一份针对GigaCrowd挑战赛的技术报告。从单目图像重建3D人群是一个具有挑战性的问题，原因在于相互遮挡、深度模糊以及复杂的空间分布。由于缺乏可用于训练鲁棒模型的大规模3D人群数据集，当前的多人体网格恢复方法在拥挤场景中难以取得令人满意的性能。在本文中，我们利用人群特征，提出了一种人群约束优化方法，以改进常见的单人体方法在人群图像上的表现。为了避免尺度变化，我们首先使用现成的检测器从原始图像中检测人体边界框和2D姿态。然后，我们利用现有的野外图像数据集训练一个单人体网格恢复网络。为了促进更合理的空间分布，我们进一步提出一种人群约束来优化单人体网络的参数。通过这种优化，我们可以使用单人体骨干网络从大规模人群图像中获得准确的姿态和形状，以及合理的绝对位置。代码将在https://github.com/boycehbz/CrowdRec公开提供。
英文摘要：
This is a technical report for the GigaCrowd challenge. Reconstructing 3D crowds from monocular images is a challenging problem due to mutual occlusions, server depth ambiguity, and complex spatial distribution. Since no large-scale 3D crowd dataset can be used to train a robust model, the current multi-person mesh recovery methods can hardly achieve satisfactory performance in crowded scenes. In this paper, we exploit the crowd features and propose a crowd-constrained optimization to improve the common single-person method on crowd images. To avoid scale variations, we first detect human bounding-boxes and 2D poses from the original images with off-the-shelf detectors. Then, we train a single-person mesh recovery network using existing in-the-wild image datasets. To promote a more reasonable spatial distribution, we further propose a crowd constraint to refine the single-person network parameters. With the optimization, we can obtain accurate body poses and shapes with reasonable absolute positions from a large-scale crowd image using a single-person backbone. The code will be publicly available at~\url{https://github.com/boycehbz/CrowdRec}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
