SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.07181 · ICCV · 2021

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

Nanxuan Zhao, Lei Yang, Ailing Zeng, Xiao Sun, Qiang Xu, Minhao Liu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

to solve the single-view 2D-to-3D pose estimation problem. While the average prediction accuracy has been improved significantly over the years, the performance on hard poses with depth ambiguity, self-occlusion, and complex or rare poses is still far from satisfactory. In this work, we target these hard poses and present a novel skeletal GNN learning solution. To be specific, we propose a hop-aware hierarchical channel-squeezing fusion layer to effectively extract relevant information from neighboring nodes while suppressing undesired noises in GNN learning. In addition, we propose a temporal-aware dynamic graph construction procedure that is robust and effective for 3D pose estimation. Experimental results on the Human3.6M dataset show that our solution achieves 10.3% average prediction accuracy improvement and greatly improves on hard poses over state-of-the-art techniques. We further apply the proposed technique on the skeleton-based action recognition task and also achieve state-of-the-art performance. Our code is available at https://github. com/ailingzengzzz/Skeletal-GNN . 23 32 41 50 59 Walk WalkToge Eat Greet Purcha. Direct Smoke Phone WalkDog Discuss Wait Pose Photo Sit SitDown MPJPE (mm) FCN[23] Multi-task[22] SRNet[45] Global-GCN[19] High-order GCN[50] Recently, various 6,2,18,19,50] are proposed in the literature for 3d pose estimation. As

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2108.07181")
get_code_for_paper("2108.07181")
have("2108.07181")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2108.07181.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2108.07181.svg)](https://syntology.ai/paper/2108.07181)

Connect an agent — have() is free.