Accurately estimating the 3D pose of humans in video sequences requires both accuracy and a well-structured architecture. With the success of transformers, we introduce the Refined Temporal Pyramidal Compression-and-Amplification (RTPCA) transformer. Exploiting the temporal dimension, RTPCA extends intra-block temporal modeling via its Temporal Pyramidal Compression-and-Amplification (TPCA) structure and refines inter-block feature interaction with a Cross-Layer Refinement (XLR) module. In particular, TPCA block exploits a temporal pyramid paradigm, reinforcing key and value representation capabilities and seamlessly extracting spatial semantics from motion sequences. We stitch these TPCA blocks with XLR that promotes rich semantic representation through continuous interaction of queries, keys, and values. This strategy embodies early-stage information with current flows, addressing typical deficits in detail and stability seen in other transformer-based methods. We demonstrate the effectiveness of RTPCA by achieving state-of-the-art results on Human3.6M, HumanEva-I, and MPI-INF-3DHP benchmarks with minimal computational overhead. The source code is available at https://github.com/hbing-l/RTPCA.

翻译：准确估计视频序列中人体三维姿态需要兼顾精度与清晰的架构设计。借助Transformer的成功，我们提出了改进型时序金字塔压缩-放大（RTPCA）Transformer。通过利用时序维度，RTPCA采用时序金字塔压缩-放大（TPCA）结构扩展块内时序建模，并利用跨层细化（XLR）模块优化块间特征交互。具体而言，TPCA模块利用时序金字塔范式增强键值与表示能力，从运动序列中无缝提取空间语义。我们通过XLR将TPCA模块串联，通过查询、键和值的持续交互促进丰富的语义表征。该策略将早期阶段信息与当前流融合，克服了其他基于Transformer方法在细节与稳定性方面的典型缺陷。我们在Human3.6M、HumanEva-I及MPI-INF-3DHP基准上以极低计算开销实现了最先进的结果，验证了RTPCA的有效性。源代码已开源至https://github.com/hbing-l/RTPCA。