3D WholeBody Pose Estimation based on Semantic Graph Attention Network and Distance Information
This work addresses 3D pose estimation for applications like human-computer interaction or animation, but it appears incremental as it builds on existing self-attention and graph convolution techniques.
The authors tackled 3D whole-body pose estimation by developing a Semantic Graph Attention Network that combines self-attention and graph convolutions, along with a Body Part Decoder and Distance Information, achieving results that exceed state-of-the-art benchmarks.
In recent years, a plethora of diverse methods have been proposed for 3D pose estimation. Among these, self-attention mechanisms and graph convolutions have both been proven to be effective and practical methods. Recognizing the strengths of those two techniques, we have developed a novel Semantic Graph Attention Network which can benefit from the ability of self-attention to capture global context, while also utilizing the graph convolutions to handle the local connectivity and structural constraints of the skeleton. We also design a Body Part Decoder that assists in extracting and refining the information related to specific segments of the body. Furthermore, our approach incorporates Distance Information, enhancing our model's capability to comprehend and accurately predict spatial relationships. Finally, we introduce a Geometry Loss who makes a critical constraint on the structural skeleton of the body, ensuring that the model's predictions adhere to the natural limits of human posture. The experimental results validate the effectiveness of our approach, demonstrating that every element within the system is essential for improving pose estimation outcomes. With comparison to state-of-the-art, the proposed work not only meets but exceeds the existing benchmarks.