End-to-End Human Pose and Mesh Reconstruction with Transformers

Abstract

We present a new method, called MEsh TRansfOrmer (METRO), to reconstruct 3D human pose and mesh vertices from a single image. Our method uses a transformer encoder to jointly model vertex-vertex and vertex-joint interactions, and outputs 3D joint coordinates and mesh vertices simultaneously. Compared to existing techniques that regress pose and shape parameters, METRO does not rely on any parametric mesh models like SMPL, thus it can be easily extended to other objects such as hands. We further relax the mesh topology and allow the transformer self-attention mechanism to freely attend between any two vertices, making it possible to learn non-local relationships among mesh vertices and joints. With the proposed masked vertex modeling, our method is more robust and effective in handling challenging situations like partial occlusions. METRO generates new state-of-the-art results for human mesh reconstruction on the public Human3.6M and 3DPW datasets. Moreover, we demonstrate the generalizability of METRO to 3D hand reconstruction in the wild, outperforming existing state-of-the-art methods on FreiHAND dataset. Code and pre-trained models are available at https://github.com/microsoft/MeshTransformer.

CVPR 2021

References in corpus (3)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Language Models are Few-Shot Learners
• Embodied Hands: Modeling and Capturing Hands and Bodies Together

Cited by in corpus (10)

• Transformers in Vision: A Survey
• TFPose: Direct Human Pose Estimation with Transformers
• Multiscale Vision Transformers
• Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
• TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation
• X-volution: On the unification of convolution and self-attention
• TokenPose: Learning Keypoint Tokens for Human Pose Estimation
• End-to-End Trainable Multi-Instance Pose Estimation with Transformers
• Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements
• Sampling Equivariant Self-attention Networks for Object Detection in Aerial Images