通过调整骨骼长度提升3D人体姿态估计精度
BLAPose: Enhancing 3D Human Pose Estimation with Bone Length Adjustment
- 用递归网络预测视频中全身骨骼长度
- 在Human3.6M上提升多个评估指标表现
- 适合需要高精度姿态估计的研究与应用
现有3D人体姿态估计方法多聚焦于回归关节位置，常忽略骨骼长度一致性与身体对称性等物理约束。本文提出一种递归神经网络架构，可捕捉整个视频序列的全局信息，实现骨骼长度的准确预测。为提升训练效果，设计了一种基于物理约束的合成骨骼长度增强策略。此外，提出一种骨骼长度调整方法，在保持骨骼方向不变的前提下，用预测值替换原始长度。实验表明，该调整过程可显著提升现有模型性能；进一步使用推断出的骨骼长度微调模型，带来明显改进。所提骨骼长度预测模型优于先前最佳结果，且调整与微调方法在Human3.6M数据集上多个指标均取得提升。
原文摘要 · Abstract (English)
Current approaches in 3D human pose estimation primarily focus on regressing 3D joint locations, often neglecting critical physical constraints such as bone length consistency and body symmetry. This work introduces a recurrent neural network architecture designed to capture holistic information across entire video sequences, enabling accurate prediction of bone lengths. To enhance training effectiveness, we propose a novel augmentation strategy using synthetic bone lengths that adhere to physical constraints. Moreover, we present a bone length adjustment method that preserves bone orientations while substituting bone lengths with predicted values. Our results demonstrate that existing 3D human pose estimation models can be significantly enhanced through this adjustment process. Furthermore, we fine-tune human pose estimation models using inferred bone lengths, observing notable improvements. Our bone length prediction model surpasses the previous best results, and our adjustment and fine-tuning method enhance performance across several metrics on the Human3.6M dataset.
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。