Related papers: Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

URL: http://arxiv.org/abs/2108.07181v2
Date: Tue, 17 Aug 2021 05:01:47 GMT
Title: Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation
Authors: Ailing Zeng, Xiao Sun, Lei Yang, Nanxuan Zhao, Minhao Liu, Qiang Xu
Abstract summary: We present a novel skeletal GNN learning solution for hard poses with depth ambiguity, self-occlusion, and complex poses. Experimental results on the Human3.6M dataset show that our solution achieves 10.3% average prediction accuracy improvement.
Score: 14.413034040734477
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Various deep learning techniques have been proposed 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.

Related papers

SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization [16.460851701725392]
We present a novel approach that optimize radiance fields with scene graphs to mitigate the influence of outlier poses. Our method incorporates an adaptive inlier-outlier confidence estimation scheme based on scene graphs. We also introduce an effective intersection-over-union (IoU) loss to optimize the camera pose and surface geometry.
arXiv Detail & Related papers (2024-07-17T15:50:17Z)
UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues [55.69339788566899]
UPose3D is a novel approach for multi-view 3D human pose estimation. It improves robustness and flexibility without requiring direct 3D annotations.
arXiv Detail & Related papers (2024-04-23T00:18:00Z)
SplatPose & Detect: Pose-Agnostic 3D Anomaly Detection [18.796625355398252]
State-of-the-art algorithms are able to detect defects in increasingly difficult settings and data modalities. We propose the novel 3D Gaussian splatting-based framework SplatPose which accurately estimates the pose of unseen views in a differentiable manner. We achieve state-of-the-art results in both training and inference speed, and detection performance, even when using less training data than competing methods.
arXiv Detail & Related papers (2024-04-10T08:48:09Z)
Occlusion Resilient 3D Human Pose Estimation [52.49366182230432]
Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. We demonstrate the effectiveness of this approach compared to state-of-the-art techniques that infer poses from single-camera sequences.
arXiv Detail & Related papers (2024-02-16T19:29:43Z)
NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation [53.25973084799954]
We present NIKI (Neural Inverse Kinematics with Invertible Neural Network), which models bi-directional errors. NIKI can learn from both the forward and inverse processes with invertible networks.
arXiv Detail & Related papers (2023-05-15T12:13:24Z)
PONet: Robust 3D Human Pose Estimation via Learning Orientations Only [116.1502793612437]
We propose a novel Pose Orientation Net (PONet) that is able to robustly estimate 3D pose by learning orientations only. PONet estimates the 3D orientation of these limbs by taking advantage of the local image evidence to recover the 3D pose. We evaluate our method on multiple datasets, including Human3.6M, MPII, MPI-INF-3DHP, and 3DPW.
arXiv Detail & Related papers (2021-12-21T12:48:48Z)
Revisiting Skeleton-based Action Recognition [107.08112310075114]
PoseC3D is a new approach to skeleton-based action recognition, which relies on a 3D heatmap instead stack a graph sequence as the base representation of human skeletons. On four challenging datasets, PoseC3D consistently obtains superior performance, when used alone on skeletons and in combination with the RGB modality.
arXiv Detail & Related papers (2021-04-28T06:32:17Z)
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training [40.933783830017035]
Estimating 3D poses from a monocular task is still a challenging task, despite the significant progress that has been made in recent years. We introduce a-temporal video network for robust 3D human pose estimation. We apply multi-scale spatial features for 2D joints or keypoints prediction in each individual frame, and multistride temporal convolutional net-works (TCNs) to estimate 3D joints or keypoints.
arXiv Detail & Related papers (2020-04-07T09:12:12Z)
Anatomy-aware 3D Human Pose Estimation with Bone-based Pose Decomposition [92.99291528676021]
Instead of directly regressing the 3D joint locations, we decompose the task into bone direction prediction and bone length prediction. Our motivation is the fact that the bone lengths of a human skeleton remain consistent across time. Our full model outperforms the previous best results on Human3.6M and MPI-INF-3DHP datasets.
arXiv Detail & Related papers (2020-02-24T15:49:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.