MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network
This work addresses the problem of accurate and efficient 3D human pose estimation for computer vision applications, offering an incremental improvement over existing transformer-based methods.
The paper tackles 3D human pose estimation by introducing MotionAGFormer, a network that combines transformer and GCNFormer streams to capture both global and local joint dependencies, achieving state-of-the-art results with P1 errors of 38.4mm on Human3.6M and 16.2mm on MPI-INF-3DHP, while using fewer parameters and being more efficient.
Recent transformer-based approaches have demonstrated excellent performance in 3D human pose estimation. However, they have a holistic view and by encoding global relationships between all the joints, they do not capture the local dependencies precisely. In this paper, we present a novel Attention-GCNFormer (AGFormer) block that divides the number of channels by using two parallel transformer and GCNFormer streams. Our proposed GCNFormer module exploits the local relationship between adjacent joints, outputting a new representation that is complementary to the transformer output. By fusing these two representation in an adaptive way, AGFormer exhibits the ability to better learn the underlying 3D structure. By stacking multiple AGFormer blocks, we propose MotionAGFormer in four different variants, which can be chosen based on the speed-accuracy trade-off. We evaluate our model on two popular benchmark datasets: Human3.6M and MPI-INF-3DHP. MotionAGFormer-B achieves state-of-the-art results, with P1 errors of 38.4mm and 16.2mm, respectively. Remarkably, it uses a quarter of the parameters and is three times more computationally efficient than the previous leading model on Human3.6M dataset. Code and models are available at https://github.com/TaatiTeam/MotionAGFormer.