Mesh Graphormer
By Kevin Qinghong Lin, Lijuan Wang, Zicheng Liu. IEEE International Conference on Computer Vision, 2021
419 citations recorded by the source corpus.
We present a graph-convolution-reinforced transformer, named Mesh Graphormer, for 3D human pose and mesh reconstruction from a single image. Recently both transformers and graph convolutional neural networks (GC-NNs) have shown promising progress in human mesh re-construction. Transformer-based approaches are effective in modeling non-local interactions among 3D mesh vertices and body joints, whereas GCNNs are good at exploiting neighborhood vertex interactions based on a pre-specified mesh topology. In this paper, we study how to combine graph convolutions and self-attentions in a transformer to model both local and global interactions. Experimental results show that our proposed method, Mesh Graphormer, significantly outperforms the previous state-of-the-art methods on multiple benchmarks, including Human3.6M, 3DPW, and FreiHAND datasets. Code and pre-trained models are available at https://github.com/microsoft/MeshGraphormer.
Subfields: Computational Mechanics, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/919ede27c84203ee0522c623f99f2315124cf164
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mechanics
- Jitendra Malik
- Angjoo Kanazawa
- Georgios Pavlakos
- David F. Fouhey
- Ilija Radosavovic
- Dandan Shan
- Jathushan Rajasegaran
- Shubham Goel
In Computer Vision and Pattern Recognition
- Jitendra Malik
- Luc Van Gool
- Trevor Darrell
- Cordelia Schmid
- Abhinav Kumar Gupta
- Andrea Vedaldi
- Andrew Zisserman
- Dacheng Tao
Citations in the corpus
- Humans in 4D: Reconstructing and Tracking Humans with Transformers (2023, methodology): “GraphCMR [36] uses a graph neural network for the prediction, METRO [42] and FastMETRO [10] use a trans-former, while Mesh Graphormer [43] adopts a hybrid be-tween the two.”
- MotionBERT: A Unified Perspective on Learning Human Motion Representations (2022, neutral): “Mesh Graphormer [59] ICCV’21 image 1 51.”
- Reconstructing Hands in 3D with Transformers (2023, methodology): “The baselines include METRO [33], Mesh Graphormer [34] and FrankMocap [49].”
- CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation (2022, neutral): “Both top-down [23,25,21,27] and bottom-up [49] approaches can do the job.”