arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2505.03445cs.CV
收藏

基于神经距离场的极坐标二维姿态先验

Polar Coordinate-Based 2D Pose Prior with Neural Distance Field

LTCI, Télécom Paris, Institut Polytechnique de Paris(LTCI,巴黎电信学院,巴黎理工学院);U2IS, ENSTA Paris, Institut Polytechnique de Paris(U2IS,巴黎ENSTA,巴黎理工学院);Ef-e-science, France(Ef-e-science,法国);SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris(SAMOVAR,巴黎南电信学院,巴黎理工学院)

Qi Gan, Sao Mai Nguyen, Eric Fenaux, Stephan Clémençon, Mounîm El Yacoubi

AI总结:

本文提出基于神经距离场的极坐标二维姿态先验方法,通过引入关节长度和非测地距离度量,并设计批量投影增强策略,在有限数据下提升跨领域姿态估计的准确性。

摘要:

人体姿态捕捉对于体育分析至关重要,能够对运动员动作进行精确评估。虽然基于深度学习的RGB视频人体姿态估计(HPE)模型在公开数据集上已取得令人瞩目的性能,但它们在真实体育场景中的有效性往往受到运动模糊、遮挡以及不同姿态表示之间的领域偏移的阻碍。对这些模型进行微调可以部分缓解此类挑战,但通常需要大规模标注数据,并且仍然难以泛化到多样化的体育环境中。为解决这些局限性,我们提出了一种基于神经距离场(NDF)的二维姿态先验引导细化方法。与仅依赖人体姿态角度表示的现有方法不同,我们引入了一种基于极坐标的表示,该表示显式地纳入关节连接长度,从而能够更准确地纠正错误的姿态估计。此外,我们定义了一种新颖的非测地距离度量,将角度偏差与径向偏差分离开来,并证明该度量比传统测地距离更适合极坐标表示。为缓解数据稀缺问题,我们开发了一种基于梯度的批量投影增强策略,通过迭代细化合成逼真的姿态样本。我们在跳远数据集上对所提方法进行了评估,证明其能够在多种姿态表示下改进二维姿态估计,使其在不同领域间具有鲁棒性。实验结果表明,我们的方法在仅需有限训练数据的情况下提升了姿态合理性。代码见:https://github.com/QGAN2019/polar-NDF。

英文摘要:

Human pose capture is essential for sports analysis, enabling precise evaluation of athletes' movements. While deep learning-based human pose estimation (HPE) models from RGB videos have achieved impressive performance on public datasets, their effectiveness in real-world sports scenarios is often hindered by motion blur, occlusions, and domain shifts across different pose representations. Fine-tuning these models can partially alleviate such challenges but typically requires large-scale annotated data and still struggles to generalize across diverse sports environments. To address these limitations, we propose a 2D pose prior-guided refinement approach based on Neural Distance Fields (NDF). Unlike existing approaches that rely solely on angular representations of human poses, we introduce a polar coordinate-based representation that explicitly incorporates joint connection lengths, enabling a more accurate correction of erroneous pose estimations. Additionally, we define a novel non-geodesic distance metric that separates angular and radial discrepancies, which we demonstrate is better suited for polar representations than traditional geodesic distances. To mitigate data scarcity, we develop a gradient-based batch-projection augmentation strategy, which synthesizes realistic pose samples through iterative refinement. Our method is evaluated on a long jump dataset, demonstrating its ability to improve 2D pose estimation across multiple pose representations, making it robust across different domains. Experimental results show that our approach enhances pose plausibility while requiring only limited training data. Code is available at: https://github.com/QGAN2019/polar-NDF.

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。

↑