paper-with-me

Papers

GraFormer: Graph Convolution Transformer for 3D Pose Estimation

2021-09-17 · Weixi Zhao, Yunjie Tian, Qixiang Ye, Jianbin Jiao, Weiqiang Wang

Exploiting relations among 2D joints plays a crucial role yet remains semi-developed in 2D-to-3D pose estimation. To alleviate this issue, we propose GraFormer, a novel transformer architecture combined with graph convolution for 3D pose estimation. The proposed GraFormer comprises two repeatedly stacked core modules, GraAttention and ChebGConv block. GraAttention enables all 2D joints to interact in global receptive field without weakening the graph structure information of joints, which introduces vital features for later modules. Unlike vanilla graph convolutions that only model the apparent relationship of joints, ChebGConv block enables 2D joints to interact in the high-order sphere, which formulates their hidden implicit relations. We empirically show the superiority of GraFormer through conducting extensive experiments across popular benchmarks. Specifically, GraFormer outperforms state of the art on Human3.6M dataset while using 18$\%$ parameters. The code is available at https://github.com/Graformer/GraFormer .

📄 PDF Abstract BibTeX arXiv:2109.08364

Code (1)

graformer/graformer 공식 구현 pytorch

Tasks

3D Pose EstimationImplicit RelationsPose Estimation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

GraFormer: Graph-Oriented Transformer for 3D Pose Estimation

2022-01-01 · CVPR 2022 1 · Weixi Zhao, Weiqiang Wang, Yunjie Tian

In 2D-to-3D pose estimation, it is important to exploit the spatial constraints of 2D joints, but it is not yet well modeled. To better model the relation of joints for 3D pose estimation, we propose an effective but…

3D Pose EstimationPose Estimation

THOR-Net: End-to-end Graformer-based Realistic Two Hands and Object Reconstruction with Self-supervision

2022-10-25 · Ahmed Tawfik Aboukhadra, Jameel Malik, Ahmed Elhayek, Nadia Robertini 외

Realistic reconstruction of two hands interacting with objects is a new and challenging problem that is essential for building personalized Virtual and Augmented Reality environments. Graph Convolutional networks (GCNs) …

Hand Pose EstimationObject ReconstructionPose Estimation

Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs

2020-06-16 · NAACL (TextGraphs) 2021 6 · Martin Schmitt, Leonardo F. R. Ribeiro, Philipp Dufter, Iryna Gurevych 외

We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only dir…

Data-to-Text GenerationDecoderKG-to-Text GenerationKnowledge Graphs+2

ShapeGraFormer: GraFormer-Based Network for Hand-Object Reconstruction from a Single Depth Map

2023-10-18 · Ahmed Tawfik Aboukhadra, Jameel Malik, Nadia Robertini, Ahmed Elhayek 외

3D reconstruction of hand-object manipulations is important for emulating human actions. Most methods dealing with challenging object manipulation scenarios, focus on hands reconstruction in isolation, ignoring physical …

3D ReconstructionObjectObject ReconstructionPose Estimation

C-MambaPose: A Physics-Informed Complex Mamba Framework for Cross-Environment WiFi Human Pose Estimation

2026-06-05 · Phuc Nguyen H arxiv

Human pose estimation (HPE) utilizing wireless WiFi signals has emerged as a promising technology owing to its device-free nature, privacy preservation, and robustness against occlusion and poor lighting. However, existi…

Pose Estimation