paper-with-me

Papers Weakly-supervised 3D Human Pose Estimation

“Weakly-supervised 3D Human Pose Estimation” 태그가 달린 논문 29편 · 필터 해제

A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation

2024-03-17 · CVPR 2024 1 · Qucheng Peng, Ce Zheng, Chen Chen

3D human pose data collected in controlled laboratory settings present challenges for pose estimators that generalize across diverse scenarios. To address this, domain generalization is employed. Current methodologies in…

3D Human Pose EstimationDomain GeneralizationPose EstimationWeakly-supervised 3D Human Pose Estimation

Automatic Labeling of Parkinson’s Disease Gait Videos with Weak Supervision

2023-06-25 · Medical Image Analysis 2023 6 · Mohsen Gholami, Rabab Ward, Ravneet Mahal, Maryam Mirian 외

Motor dysfunction in Parkinson’s Disease (PD) patients is typically assessed by clinicians employing the Movement Disorder Society’s Unified Parkinson’s Disease Rating Scale (MDS-UPDRS). Such comprehensive clinical asses…

3D Human Pose EstimationPose EstimationWeakly-supervised 3D Human Pose Estimation

Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation

2022-04-05 · NeurIPS 2021 12 · Jogendra Nath Kundu, Siddharth Seth, Anirudh Jamkhandi, Pradyumna YM 외

Available 3D human pose estimation approaches leverage different forms of strong (2D/3D pose) or weak (multi-view or depth) paired supervision. Barring synthetic or in-studio domains, acquiring such supervision for each …

3D Human Pose EstimationDecoderPose EstimationRelation+2

Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation

2022-03-29 · CVPR 2022 1 · Jogendra Nath Kundu, Siddharth Seth, Pradyumna YM, Varun Jampani 외

The advances in monocular 3D human pose estimation are dominated by supervised techniques that require large-scale 2D/3D pose annotations. Such methods often behave erratically in the absence of any provision to discard …

3D Human Pose EstimationDomain AdaptationMonocular 3D Human Pose EstimationPose Estimation+3

On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation

2022-03-29 · Soumava Kumar Roy, Leonardo Citraro, Sina Honari, Pascal Fua

Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of ground-truth 3D labels is labor intensive and time consuming, recent a…

3D Human Pose Estimation3D Pose EstimationFormPose Estimation+2

AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation

2021-12-22 · CVPR 2022 1 · Mohsen Gholami, Bastian Wandt, Helge Rhodin, Rabab Ward 외

This paper addresses the problem of cross-dataset generalization of 3D human pose estimation models. Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop. Previous methods have mai…

3D Human Pose EstimationDiversityMotion GenerationPose Estimation+1

Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition

2021-09-19 · ICCV 2021 10 · Xiaodan Hu, Narendra Ahuja

Dance experts often view dance as a hierarchy of information, spanning low-level (raw images, image sequences), mid-levels (human poses and bodypart movements), and high-level (dance genre). We propose a Hierarchical Dan…

3D Pose EstimationPose EstimationUnsupervised 3D Human Pose EstimationVideo Recognition+1

Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry

2021-08-17 · Arij Bouazizi, Julian Wiederer, Ulrich Kressel, Vasileios Belagiannis

We present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera system and 2D body pose estimates for each view. To train our model, represented by a deep n…

3D Human Pose EstimationPose EstimationSelf-Supervised LearningWeakly-supervised 3D Human Pose Estimation+1

MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision

2021-08-10 · CVPR 2022 1 · Ben Usman, Andrea Tagliasacchi, Kate Saenko, Avneesh Sud

In the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date. We show how to train a neural model to perform this task with high precision and mi…

3D Human Pose EstimationPose EstimationWeakly-supervised 3D Human Pose Estimation

Heuristic Weakly Supervised 3D Human Pose Estimation

2021-05-23 · Shuangjun Liu, Michael Wan, Sarah Ostadabbas

Monocular 3D human pose estimation from RGB images has attracted significant attention in recent years. However, recent models depend on supervised training with 3D pose ground truth data or known pose priors for their t…

3D Human Pose Estimation3D Pose EstimationMonocular 3D Human Pose EstimationPose Estimation+1

Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network

2021-05-23 · Guoliang Hua, Hong Liu, Wenhao Li, Qian Zhang 외

Although monocular 3D human pose estimation methods have made significant progress, it is far from being solved due to the inherent depth ambiguity. Instead, exploiting multi-view information is a practical way to achiev…

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose EstimationWeakly-supervised 3D Human Pose Estimation+1

TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video

2021-05-14 · Mohsen Gholami, Ahmad Rezaei, Helge Rhodin, Rabab Ward 외

Estimating 3D human poses from video is a challenging problem. The lack of 3D human pose annotations is a major obstacle for supervised training and for generalization to unseen datasets. In this work, we address this pr…

3D Human Pose EstimationPose EstimationWeakly-supervised 3D Human Pose Estimation

PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation

2021-05-06 · CVPR 2021 1 · Kehong Gong, Jianfeng Zhang, Jiashi Feng

Existing 3D human pose estimators suffer poor generalization performance to new datasets, largely due to the limited diversity of 2D-3D pose pairs in the training data. To address this problem, we present PoseAug, a new …

3D Human Pose EstimationData AugmentationDiversityMonocular 3D Human Pose Estimation+2

CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild

2020-11-30 · CVPR 2021 1 · Bastian Wandt, Marco Rudolph, Petrissa Zell, Helge Rhodin 외

Human pose estimation from single images is a challenging problem in computer vision that requires large amounts of labeled training data to be solved accurately. Unfortunately, for many human activities (\eg outdoor spo…

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose EstimationWeakly-supervised 3D Human Pose Estimation

Error Bounds of Projection Models in Weakly Supervised 3D Human Pose Estimation

2020-10-23 · Nikolas Klug, Moritz Einfalt, Stephan Brehm, Rainer Lienhart

The current state-of-the-art in monocular 3D human pose estimation is heavily influenced by weakly supervised methods. These allow 2D labels to be used to learn effective 3D human pose recovery either directly from image…

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose EstimationPosition+1

Cascaded deep monocular 3D human pose estimation with evolutionary training data

2020-06-14 · CVPR 2020 6 · Shichao Li, Lei Ke, Kevin Pratama, Yu-Wing Tai 외

End-to-end deep representation learning has achieved remarkable accuracy for monocular 3D human pose estimation, yet these models may fail for unseen poses with limited and fixed training data. This paper proposes a nove…

3D Human Pose EstimationData AugmentationMonocular 3D Human Pose EstimationPose Estimation+3

Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis

2020-04-09 · CVPR 2020 6 · Jogendra Nath Kundu, Siddharth Seth, Varun Jampani, Mugalodi Rakesh 외

Camera captured human pose is an outcome of several sources of variation. Performance of supervised 3D pose estimation approaches comes at the cost of dispensing with variations, such as shape and appearance, that may be…

3D Human Pose Estimation3D Pose EstimationDisentanglementImage Generation+4

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

2020-03-17 · CVPR 2020 6 · Umar Iqbal, Pavlo Molchanov, Jan Kautz

One major challenge for monocular 3D human pose estimation in-the-wild is the acquisition of training data that contains unconstrained images annotated with accurate 3D poses. In this paper, we address this challenge by …

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose EstimationWeakly-superavised 3D Human Pose Estimation+1

TexturePose: Supervising Human Mesh Estimation with Texture Consistency

2019-10-24 · ICCV 2019 10 · Georgios Pavlakos, Nikos Kolotouros, Kostas Daniilidis

This work addresses the problem of model-based human pose estimation. Recent approaches have made significant progress towards regressing the parameters of parametric human body models directly from images. Because of th…

Pose EstimationWeakly-supervised 3D Human Pose Estimation

On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos

2019-10-01 · ICCV 2019 10 · Zhi Li, Xuan Wang, Fei Wang, Peilin Jiang

The premise of training an accurate 3D human pose estimation network is the possession of huge amount of richly annotated training data. Nonetheless, manually obtaining rich and accurate annotations is, even not impossib…

3D Human Pose EstimationPose EstimationWeakly-supervised 3D Human Pose Estimation
1–20 / 29 다음 →