Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation
This addresses the problem of accurate and efficient 3D human pose estimation for video analysis, representing an incremental improvement over existing transformer-based methods.
The paper tackles 3D human pose estimation in videos by introducing the RTPCA transformer, which achieves state-of-the-art results on benchmarks like Human3.6M, HumanEva-I, and MPI-INF-3DHP with minimal computational overhead.
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.