Quater-GCN: Enhancing 3D Human Pose Estimation with Orientation and Semi-supervised Training

• URL: http://arxiv.org/abs/2404.19279v3
• Date: Fri, 11 Oct 2024 11:30:53 GMT
• Title: Quater-GCN: Enhancing 3D Human Pose Estimation with Orientation and Semi-supervised Training
• Abstract summary: We introduce Quater-GCN, a directed graph convolutional network tailored to enhance pose estimation by orientation. Q-GCN excels by not only capturing the spatial dependencies among node joints through their coordinates but also integrating the dynamic context of bone rotations in 2D space. We complement our model with a semi-supervised training strategy that leverages unlabeled data, addressing the challenge of limited orientation ground truth data.
• Score: 11.4616369582769
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D human pose estimation is a vital task in computer vision, involving the prediction of human joint positions from images or videos to reconstruct a skeleton of a human in three-dimensional space. This technology is pivotal in various fields, including animation, security, human-computer interaction, and automotive safety, where it promotes both technological progress and enhanced human well-being. The advent of deep learning significantly advances the performance of 3D pose estimation by incorporating temporal information for predicting the spatial positions of human joints. However, traditional methods often fall short as they primarily focus on the spatial coordinates of joints and overlook the orientation and rotation of the connecting bones, which are crucial for a comprehensive understanding of human pose in 3D space. To address these limitations, we introduce Quater-GCN (Q-GCN), a directed graph convolutional network tailored to enhance pose estimation by orientation. Q-GCN excels by not only capturing the spatial dependencies among node joints through their coordinates but also integrating the dynamic context of bone rotations in 2D space. This approach enables a more sophisticated representation of human poses by also regressing the orientation of each bone in 3D space, moving beyond mere coordinate prediction. Furthermore, we complement our model with a semi-supervised training strategy that leverages unlabeled data, addressing the challenge of limited orientation ground truth data. Through comprehensive evaluations, Q-GCN has demonstrated outstanding performance against current state-of-the-art methods.

Related papers

• SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video [88.79625979053873]
  We propose a novel framework, SpaceEra, for pre-trained vision-language models (VLMs)<n>We extend the original framework into a comprehensive system, termed SpaceEra++, which spans data construction, model design, training optimization, and prompting inference.<n>In addition, to enhance spatial reasoning, we develop SpaceAlign, which enforces pairwise object constraints by jointly exploiting absolute coordinates and relative spatial relations.
  arXiv  Detail & Related papers  (2026-07-02T06:56:29Z)
• RoboPCA: Pose-centered Affordance Learning from Human Demonstrations for Robot Manipulation [35.68205801897266]
  RoboPCA is a pose-centered affordance prediction framework that jointly predicts task-appropriate contact regions and poses conditioned on instructions.<n>Human2Afford is a data curation pipeline that automatically recovers scene-level 3D information and infers pose-centered affordance annotations from human demonstrations.<n>RoboPCA outperforms baseline methods on image datasets, simulation, and real robots, and exhibits strong generalization across tasks and categories.
  arXiv  Detail & Related papers  (2026-03-08T15:46:04Z)
• GRACE: Estimating Geometry-level 3D Human-Scene Contact from 2D Images [54.602947113980655]
  Estimating the geometry level of human-scene contact aims to ground specific contact surface points at 3D human geometries.<n> GRACE (Geometry-level Reasoning for 3D Human-scene Contact Estimation) is a new paradigm for 3D human contact estimation.<n>It incorporates a point cloud encoder-decoder architecture along with a hierarchical feature extraction and fusion module.
  arXiv  Detail & Related papers  (2025-05-10T09:25:46Z)
• 3D Human Pose Estimation via Spatial Graph Order Attention and Temporal Body Aware Transformer [5.303583360581161]
  We propose a new method that exploits the graph modeling capability of GCN to represent each skeleton with multiple graphs of different orders.<n>The resulting spatial features of the sequence are processed using a proposed temporal Body Aware Transformer.<n>Experiments on Human3.6m, MPIINF-3DHP, and HumanEva-I datasets demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2025-05-02T04:58:04Z)
• Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms [17.801307669723634]
  We propose a novel framework that conducts global transformations between pose positions. A Pose Augmentor is incorporated to address variations in human posture and body size. The proposed method outperforms state-of-the-art approaches and even outperforms the target-trained model.
  arXiv  Detail & Related papers  (2025-04-17T06:57:20Z)
• 3D-UGCN: A Unified Graph Convolutional Network for Robust 3D Human Pose Estimation from Monocular RGB Images [17.673385426594418]
  This paper proposes an improved method based on the spatial-temporal graph convolution net-work (UGCN) to address the issue of missing human posture skeleton sequences in single-view videos. We present the improvedN, which allows the network to process 3D human pose data and improves the 3D human pose skeleton sequence.
  arXiv  Detail & Related papers  (2024-07-23T02:50:27Z)
• STGFormer: Spatio-Temporal GraphFormer for 3D Human Pose Estimation in Video [7.345621536750547]
  This paper presents a graph-based framework for 3D human pose estimation in video. Specifically, we develop a graph-based attention mechanism, integrating graph information directly into the respective attention layers. We demonstrate that our method achieves significant stateof-the-art performance in 3D human pose estimation.
  arXiv  Detail & Related papers  (2024-07-14T06:45:27Z)
• Graph and Skipped Transformer: Exploiting Spatial and Temporal Modeling Capacities for Efficient 3D Human Pose Estimation [36.93661496405653]
  We take a global approach to exploit Transformer-temporal information with a concise Graph and Skipped Transformer architecture. Specifically, in 3D pose stage, coarse-grained body parts are deployed to construct a fully data-driven adaptive model. Experiments are conducted on Human3.6M, MPI-INF-3DHP and Human-Eva benchmarks.
  arXiv  Detail & Related papers  (2024-07-03T10:42:09Z)
• Social-Transmotion: Promptable Human Trajectory Prediction [65.80068316170613]
  Social-Transmotion is a generic Transformer-based model that exploits diverse and numerous visual cues to predict human behavior. Our approach is validated on multiple datasets, including JTA, JRDB, Pedestrians and Cyclists in Road Traffic, and ETH-UCY.
  arXiv  Detail & Related papers  (2023-12-26T18:56:49Z)
• Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery [70.66865453410958]
  Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. We propose a novel framework that relies only on silhouette supervision to adapt a source-trained model-based regressor. We develop a series of convolution-friendly spatial transformations in order to disentangle a topological-skeleton representation from the raw silhouette.
  arXiv  Detail & Related papers  (2022-04-04T06:58:15Z)
• Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos [47.601288796052714]
  Graph Convolution Network (GCN) has been successfully used for 3D human pose estimation in videos. New Dynamical Graph Network (DGNet) can estimate 3D pose by adaptively learning spatial/temporal joint relations from videos.
  arXiv  Detail & Related papers  (2021-09-15T15:06:19Z)
• THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers [67.8628917474705]
  THUNDR is a transformer-based deep neural network methodology to reconstruct the 3d pose and shape of people. We show state-of-the-art results on Human3.6M and 3DPW, for both the fully-supervised and the self-supervised models. We observe very solid 3d reconstruction performance for difficult human poses collected in the wild.
  arXiv  Detail & Related papers  (2021-06-17T09:09:24Z)
• TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild [77.59069361196404]
  TRiPOD is a novel method for predicting body dynamics based on graph attentional networks. To incorporate a real-world challenge, we learn an indicator representing whether an estimated body joint is visible/invisible at each frame. Our evaluation shows that TRiPOD outperforms all prior work and state-of-the-art specifically designed for each of the trajectory and pose forecasting tasks.
  arXiv  Detail & Related papers  (2021-04-08T20:01:00Z)
• Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos [33.974241749058585]
  We propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses. In particular, we introduce a human-joint GCN, which employs the 2D pose estimator's confidence scores to improve the pose estimation results. The two GCNs work together to estimate the spatial frame-wise 3D poses and can make use of both visible joint and bone information in the target frame to estimate the occluded or missing human-part information.
  arXiv  Detail & Related papers  (2020-12-22T03:01:19Z)
• HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation [54.23770284299979]
  This paper introduces a novel form of supervision - Hierarchical Multi-person Ordinal Relations (HMOR) HMOR encodes interaction information as the ordinal relations of depths and angles hierarchically. An integrated top-down model is designed to leverage these ordinal relations in the learning process. The proposed method significantly outperforms state-of-the-art methods on publicly available multi-person 3D pose datasets.
  arXiv  Detail & Related papers  (2020-08-01T07:53:27Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.