提出SCJD框架，让3D人体姿态估计更快更准。
SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation
- 用稀疏相关性下采样减少输入冗余，保留帧间关联。
- 通过动态注意力蒸馏，提升学生网络对关节关系的捕捉能力。
- 适合需要实时推理的3D姿态估计场景，如动作识别与交互分析。
现有3D人体姿态估计方法虽精度高，但计算开销大、推理慢；而传统知识蒸馏无法有效处理关节间的空间关系及多帧输入的时间相关性。本文提出稀疏相关性与联合蒸馏（SCJD）框架，平衡效率与精度。SCJD引入稀疏相关性输入序列下采样，降低学生网络输入冗余，同时保留帧间相关性。为实现高效知识迁移，提出动态关节空间注意力蒸馏：包括动态关节嵌入蒸馏，利用教师网络的多帧上下文特征增强学生特征表示；相邻关节注意力蒸馏，提升学生网络对邻近关节关系的关注，改善空间理解。此外，时间一致性蒸馏通过上采样与全局监督对齐师生网络的时间相关性。大量实验表明，SCJD达到当前最优性能。代码已开源：https://github.com/wileychan/SCJD。
原文摘要 · Abstract (English)
Existing 3D Human Pose Estimation (HPE) methods achieve high accuracy but suffer from computational overhead and slow inference, while knowledge distillation methods fail to address spatial relationships between joints and temporal correlations in multi-frame inputs. In this paper, we propose Sparse Correlation and Joint Distillation (SCJD), a novel framework that balances efficiency and accuracy for 3D HPE. SCJD introduces Sparse Correlation Input Sequence Downsampling to reduce redundancy in student network inputs while preserving inter-frame correlations. For effective knowledge transfer, we propose Dynamic Joint Spatial Attention Distillation, which includes Dynamic Joint Embedding Distillation to enhance the student's feature representation using the teacher's multi-frame context feature, and Adjacent Joint Attention Distillation to improve the student network's focus on adjacent joint relationships for better spatial understanding. Additionally, Temporal Consistency Distillation aligns the temporal correlations between teacher and student networks through upsampling and global supervision. Extensive experiments demonstrate that SCJD achieves state-of-the-art performance. Code is available at https://github.com/wileychan/SCJD.
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。