paper-with-me

Papers Unsupervised 3D Human Pose Estimation

“Unsupervised 3D Human Pose Estimation” 태그가 달린 논문 16편 · 필터 해제

Unsupervised 3D Human Pose Estimation via Conditional Multi-view Ancestral Sampling

2026-05-15 · Ryohei Goto, Takuya Fujihashi, Shunsuke Saruwatari, Fumio Okura arxiv

We propose a method of estimating a 3D human pose from a single view without 3D supervision. The key to our method is to leverage the 2D diffusion priors of motion diffusion models (MDMs) pre-trained on large 2D human po…

Unsupervised 3D Human Pose Estimation3D Pose Estimation

Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation

2023-12-12 · Yuchen Yang, Yu Qiao, Xiao Sun

Automatic estimation of 3D human pose from monocular RGB images is a challenging and unsolved problem in computer vision. In a supervised manner, approaches heavily rely on laborious annotations and present hampered gene…

3D Pose EstimationDiversityPose EstimationUnsupervised 3D Human Pose Estimation

LInKs "Lifting Independent Keypoints" -- Partial Pose Lifting for Occlusion Handling with Improved Accuracy in 2D-3D Human Pose Estimation

2023-09-13 · Peter Hardy, Hansung Kim

We present LInKs, a novel unsupervised learning method to recover 3D human poses from 2D kinematic skeletons obtained from a single image, even when occlusions are present. Our approach follows a unique two-step process,…

3D Human Pose EstimationAttributeDimensionality ReductionNormalising Flows+3

Unsupervised 3D Keypoint Discovery with Multi-View Geometry

2022-11-23 · Sina Honari, Chen Zhao, Mathieu Salzmann, Pascal Fua

Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation of body joints or via marker-based joint localization using …

3D Human Pose EstimationKeypoint EstimationPose EstimationUnsupervised 3D Human Pose Estimation

CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation

2022-08-01 · Zhihao LI, Jianzhuang Liu, Zhensong Zhang, Songcen Xu 외

Top-down methods dominate the field of 3D human pose and shape estimation, because they are decoupled from human detection and allow researchers to focus on the core problem. However, cropping, their first step, discards…

3D human pose and shape estimation3D Human Pose EstimationHuman DetectionHuman Mesh Recovery+1

Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior

2022-07-12 · Buzhen Huang, Yuan Shu, Jingyi Ju, Yangang Wang

Although significant progress has been achieved on monocular maker-less human motion capture in recent years, it is still hard for state-of-the-art methods to obtain satisfactory results in occlusion scenarios. There are…

3D Human Pose EstimationUnsupervised 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

ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses

2021-12-14 · CVPR 2022 1 · Bastian Wandt, James J. Little, Helge Rhodin

Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does not yet exist for many human activities since 3D annotation req…

3D Human Pose EstimationPose EstimationUnsupervised 3D Human Pose EstimationUnsupervised Human Pose Estimation

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

SVMAC: Unsupervised 3D Human Pose Estimation from a Single Image with Single-view-multi-angle Consistency

2021-06-10 · Yicheng Deng, Cheng Sun, Jiahui Zhu, Yongqi Sun

Recovering 3D human pose from 2D joints is still a challenging problem, especially without any 3D annotation, video information, or multi-view information. In this paper, we present an unsupervised GAN-based model consis…

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose EstimationUnsupervised 3D Human Pose Estimation

Towards Alleviating the Modeling Ambiguity of Unsupervised Monocular 3D Human Pose Estimation

2021-01-01 · ICCV 2021 10 · Zhenbo Yu, Bingbing Ni, Jingwei Xu, Junjie Wang 외

In this work, we study the ambiguity problem in the task of unsupervised 3D human pose estimation from 2D counterpart. On one hand, without explicit annotation, the scale of 3D pose is difficult to be accurately capt…

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose EstimationUnsupervised 3D Human Pose Estimation

Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation

2020-12-17 · Chenxin Xu, Siheng Chen, Maosen Li, Ya zhang

We propose a novel method based on teacher-student learning framework for 3D human pose estimation without any 3D annotation or side information. To solve this unsupervised-learning problem, the teacher network adopts po…

3D Human Pose EstimationKnowledge DistillationPose EstimationUnsupervised 3D Human Pose Estimation

Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimation

2020-08-04 · ECCV 2020 8 · Jogendra Nath Kundu, Ambareesh Revanur, Govind Vitthal Waghmare, Rahul Mysore Venkatesh 외

We present a deployment friendly, fast bottom-up framework for multi-person 3D human pose estimation. We adopt a novel neural representation of multi-person 3D pose which unifies the position of person instances with the…

2D Pose Estimation3D Human Pose Estimation3D Multi-Person Pose Estimation3D Pose Estimation+4

Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation

2020-06-24 · Jogendra Nath Kundu, Siddharth Seth, Rahul M. V, Mugalodi Rakesh 외

Estimation of 3D human pose from monocular image has gained considerable attention, as a key step to several human-centric applications. However, generalizability of human pose estimation models developed using supervisi…

3D Human Pose Estimation3D Pose EstimationDisentanglementPose Estimation+1

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
1–16 / 16