☆ 4.5 Article

Self-supervised method for 3D human pose estimation with consistent shape and viewpoint factorization

APPLIED INTELLIGENCE (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

SelfPose: 3D Egocentric Pose Estimation From a Headset Mounted Camera

Denis Tome et al.

Summary: We propose a new method for egocentric 3D body pose estimation using a downward looking fish-eye camera on a head mounted virtual reality device. Our approach addresses the challenges of self-occlusions and perspective distortions with a novel encoder-decoder architecture and a multi-branch decoder. Experimental results on synthetic and real-world datasets demonstrate the effectiveness of our method in achieving higher accuracy compared to existing approaches.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation

Kun Zhou et al.

Summary: This work addresses the challenge of estimating 3D human pose from a single image. It introduces an intermediate state called "Part-Centric Heatmap Triplets" (HEMlets) to bridge the gap between the 2D observation and 3D interpretation. The proposed method achieves significant performance improvement over existing methods and supports training with weakly-annotated relative depth information.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Locally Connected Network for Monocular 3D Human Pose Estimation

Hai Ci et al.

Summary: In this paper, an approach for estimating 3D human pose from monocular images is presented. By combining graph convolutional network (GCN) with locally connected network (LCN), the proposed approach achieves better performance on benchmark datasets and demonstrates strong generalization ability.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

UniPose plus : A Unified Framework for 2D and 3D Human Pose Estimation in Images and Videos

Bruno Artacho et al.

Summary: We propose UniPose+, a unified framework for 2D and 3D human pose estimation in images and videos. The framework leverages multi-scale feature representations and achieves pose estimation without increasing network size and postprocessing. Our results demonstrate that UniPose+ is a robust and efficient architecture.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Fast and Robust Multi-Person 3D Pose Estimation and Tracking From Multiple Views

Junting Dong et al.

Summary: This paper addresses the problem of reconstructing 3D poses of multiple people from a few calibrated camera views. The proposed approach uses a multi-way matching algorithm to cluster detected 2D poses and infer the 3D poses of each person efficiently. It also combines geometric and appearance cues for cross-view matching and proposes an efficient tracking method.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Monocular 3D Pose Estimation via Pose Grammar and Data Augmentation

Yuanlu Xu et al.

Summary: This paper proposes a pose grammar model for 3D human pose estimation from a monocular RGB image. The model leverages the estimated 2D pose as input and learns a mapping function to convert it into 3D pose. The model consists of a base network and bidirectional RNNs to capture pose-aligned features and incorporate knowledge about human body configuration. The research also improves model robustness through a data augmentation algorithm. Validation on 3D human pose benchmarks and cross-view evaluation demonstrates the effectiveness of the proposed method in handling these challenges.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

MannequinChallenge: Learning the Depths of Moving People by Watching Frozen People

Zhengqi Li et al.

Summary: The method leverages human depth priors and multi-view stereo reconstruction to generate training data, then uses motion parallax cues from static areas for depth prediction, showing improvement over state-of-the-art monocular depth prediction methods and demonstrating various 3D effects.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Context Modeling in 3D Human Pose Estimation: A Unified Perspective

Xiaoxuan Ma et al.

Summary: Comparing pictorial structure model (PSM) and graph neural network (GNN) methods, it was found that the end-to-end training scheme in GNN and the limb length constraints in PSM are two complementary factors for improving results.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

SimPoE: Simulated Character Control for 3D Human Pose Estimation

Ye Yuan et al.

Summary: SimPoE is a simulation-based approach for 3D human pose estimation that integrates image-based kinematic inference and physics-based dynamics modeling. The policy includes a learnable kinematic pose refinement unit to iteratively refine pose estimates, achieving accurate and physically plausible results.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks

Yu Cheng et al.

Summary: The proposed method integrates top-down and bottom-up approaches to address challenges in multi-person pose estimation, such as inter-person occlusion and scale variations. A two-person pose discriminator is introduced to assess natural interactions, unlike traditional single-person pose discriminators. Additionally, a semi-supervised method is utilized to overcome the scarcity of 3D ground-truth data, showing the effectiveness of the approach in quantitative and qualitative evaluations.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo

Jiahao Lin et al.

Summary: The study introduces a multi-view 3D pose estimation approach based on plane sweep stereo, which simultaneously addresses cross-view fusion and 3D pose reconstruction through depth regression and cross-view consistency constraints. Using a coarse-to-fine scheme, it first regresses person-level depth followed by joint-level relative depth estimation for accurate pose reconstruction.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep K-SVD Denoising

Meyer Scetbon et al.

Summary: This study focuses on the K-SVD denoising algorithm, proposing a supervised deep architecture for optimized denoising. The proposed architecture, with a small number of learnable parameters, substantially outperforms the classical K-SVD algorithm.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Feature Boosting Network For 3D Pose Estimation

Jun Liu et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Cascaded Deep Monocular 3D Human Pose Estimation with Evolutionary Training Data

Shichao Li et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild

Umar Iqbal et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

3D Human Pose Machines with Self-Supervised Learning

Keze Wang et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Robust 3D Human Pose Estimation from Single Images or Video Sequences

Chunyu Wang et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning

Chaoyang Wang et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation

Bastian Wandt et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation

Xipeng Chen et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations

Ikhsanul Habibie et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Semantic Graph Convolutional Networks for 3D Human Pose Regression

Long Zhao et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Unsupervised 3D Pose Estimation with Geometric Self-Supervision

Ching-Hang Chen et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A dual-source approach for 3D human pose estimation from single images

Umar Iqbal et al.

COMPUTER VISION AND IMAGE UNDERSTANDING (2018)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Learning Monocular 3D Human Pose Estimation from Multi-view Images

Helge Rhodin et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation

Bugra Tekin et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision

Hsiao-Yu Fish Tung et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

A simple yet effective baseline for 3d human pose estimation

Julieta Martinez et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Harvesting Multiple Views for Marker-less 3D Human Pose Annotations

Georgios Pavlakos et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose

Georgios Pavlakos et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Dictionary Learning for Sparse Coding: Algorithms and Convergence Analysis

Chenglong Bao et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2016)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments

Catalin Ionescu et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2014)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.