Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
基于姿态约束的 3D 人体网格细化算法. |
| Alternate Title: |
Pose-Constrained 3D Human Mesh Refinement Algorithm. |
| Συγγραφείς: |
朱 炜1, 吉根林1 glji@njnu.edu.cn, 王泽宇1, 李 宁1 |
| Πηγή: |
Journal of Nanjing University of Aeronautics & Astronautics / Nanjing Hangkong Hangtian Daxue Xuebao. Apr2026, Vol. 58 Issue 2, p449-456. 8p. |
| Θεματικοί όροι: |
*Mathematical optimization, *Physical characteristics (Human body), *Virtual reality software, *Augmented reality, *Sports sciences |
| Abstract (English): |
3D human mesh recovery (HMR) has extensive applications in virtual reality, augmented reality, autonomous driving, and sports science. However, the existing methods suffer from imprecise alignment between 3D models and 2D keypoints and often neglect the inherent symmetry and proportion constraints of the human body, resulting in recovered meshes that violate fundamental human characteristics. Our paper proposes a pose-constrained human mesh refinement (PC-HMR) algorithm that optimizes shape and pose parameters through constraint fusion. For shape parameter optimization, we introduce human body symmetry features and skeletal proportion constraints. For pose parameter optimization, we designe a multi-algorithm fusion framework that systematically integrates complementary algorithms to replace traditional single-path selection mechanisms. We evaluate the proposed method in two standard datasets: 3DPW and Human3.6M. Experimental results demonstrate that PC-HMR achieve superior performance compared to existing state-of-the-art methods. Ablation studies further validate the contribution of each module to overall performance. [ABSTRACT FROM AUTHOR] |
| Abstract (Chinese): |
3D 人体网格恢复 (Human mesh recovery, HMR) 在虚拟现实、增强现实、自动驾驶和运动科学等领域具有 广泛应用前景。然而, 现有方法面临着 3D 模型与 2D 关键点无法精确对齐的问题, 且在恢复过程中常忽视人体 固有的对称性和比例约束, 导致恢复的 3D 人体网格模型不符合人体基本特征。本文提出了一种基于姿态约束 的人体网格细化 (Pose-constrained human mesh refinement, PC-HMR) 算法, 通过多维约束融合策略优化形状参 数和姿态参数。在形状参数优化方面, 引入人体对称性特征和骨骼比例约束; 在姿态参数优化方面, 设计了一种 多算法融合的姿态约束建模框架, 通过系统性整合多种互补算法来替代传统的乘法路径选择机制。为了评估本 文方法的有效性, 在 3DPW 和 Human3.6M 两个标准数据集上进行了实验。实验结果表明, 相比现有最优方法, PC-HMR 综合性能更优。消融实验进一步验证了各模块对算法性能的影响。 [ABSTRACT FROM AUTHOR] |
| Βάση Δεδομένων: |
Academic Search Index |