MeshLeTemp: Leveraging the Learnable Vertex-Vertex Relationship to Generalize Human Pose and Mesh Reconstruction for In-the-Wild Scenes

We present MeshLeTemp, a powerful method for 3D human pose and mesh reconstruction from a single image. In terms of human body priors encoding, we propose using a learnable template human mesh instead of a constant template utilized by previous state-of-the-art methods. The proposed learnable template reflects not only vertex-vertex interactions but also the human pose and body shape, being able to adapt to diverse images. We also introduce a strategy to enrich the training data that contains both 2D and 3D annotations. We conduct extensive experiments to show the generalizability of our method and the effectiveness of our data strategy. As one of our ablation studies, we adapt MeshLeTemp to another domain which is 3D hand reconstruction.