通过骨骼几何关系增强人体姿态估计，提升遮挡与快速运动下的准确性。
PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimation
- 构建关节与骨骼双图结构，分别捕捉局部依赖关系。
- 引入跨注意力模块建模骨骼方向与关节特征的关联，提升空间一致性。
- 动态融合机制自适应整合多源信息，适合复杂场景应用。
现有单目3D人体姿态估计方法主要依赖关节位置特征，忽视了骨骼内部的方向与角度关联性，导致在关节遮挡或快速运动时产生不合理姿态。为此，我们提出PoseGRAF框架：首先构建关节与骨骼双图卷积结构，有效捕捉局部依赖；引入跨注意力模块建模骨骼方向与关节特征间的相互依赖；在此基础上设计动态融合模块，利用关节与骨骼的关联关系自适应融合两类特征；最后以残差方式融入改进的Transformer编码器生成最终输出。在Human3.6M和MPI-INF-3DHP数据集上的实验表明，本方法超越现有最优模型；对真实场景视频的额外评估进一步验证了其泛化能力。代码已公开于https://github.com/iCityLab/PoseGRAF。
原文摘要 · Abstract (English)
Existing monocular 3D pose estimation methods primarily rely on joint positional features, while overlooking intrinsic directional and angular correlations within the skeleton. As a result, they often produce implausible poses under joint occlusions or rapid motion changes. To address these challenges, we propose the PoseGRAF framework. We first construct a dual graph convolutional structure that separately processes joint and bone graphs, effectively capturing their local dependencies. A Cross-Attention module is then introduced to model interdependencies between bone directions and joint features. Building upon this, a dynamic fusion module is designed to adaptively integrate both feature types by leveraging the relational dependencies between joints and bones. An improved Transformer encoder is further incorporated in a residual manner to generate the final output. Experimental results on the Human3.6M and MPI-INF-3DHP datasets show that our method exceeds state-of-the-art approaches. Additional evaluations on in-the-wild videos further validate its generalizability. The code is publicly available at https://github.com/iCityLab/PoseGRAF.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。