Filters








1,035 Hits in 9.0 sec

Temporal-Aware Self-Supervised Learning for 3D Hand Pose and Mesh Estimation in Videos [article]

Liangjian Chen, Shih-Yao Lin, Yusheng Xie, Yen-Yu Lin, Xiaohui Xie
2020 arXiv   pre-print
By en-forcing temporal consistency constraints, TASSN learns 3Dhand poses and meshes from videos with only 2D keypointposition annotations.  ...  We leverage these two obser-vations to develop a self-supervised learning model calledtemporal-aware self-supervised network (TASSN).  ...  Conclusions We propose a video-based hand pose estimation model, temporal-aware self-supervised network (TASSN), to learn and infer 3D hand pose and mesh from RGB videos.  ... 
arXiv:2012.03205v1 fatcat:bijwjl5okffixmzbxnoorltrse

Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time [article]

Shaowei Liu, Hanwen Jiang, Jiarui Xu, Sifei Liu, Xiaolong Wang
2021 arXiv   pre-print
To tackle these challenges, we propose a unified framework for estimating the 3D hand and object poses with semi-supervised learning.  ...  Going beyond limited 3D annotations in a single image, we leverage the spatial-temporal consistency in large-scale hand-object videos as a constraint for generating pseudo labels in semi-supervised learning  ...  This work was supported, in part, by grants from DARPA LwLL, NSF 1730158 CI-New: Cognitive Hardware and Software Ecosystem Community Infrastructure (CHASE-CI), NSF ACI-1541349 CC*DNI Pacific Research Platform  ... 
arXiv:2106.05266v1 fatcat:ig3f2sw4z5ezlfpipw77y5i5tm

Consistent 3D Hand Reconstruction in Video via self-supervised Learning [article]

Zhigang Tu, Zhisheng Huang, Yujin Chen, Di Kang, Linchao Bao, Bisheng Yang, Junsong Yuan
2022 arXiv   pre-print
Thus we propose S^2HAND, a self-supervised 3D hand reconstruction model, that can jointly estimate pose, shape, texture, and the camera viewpoint from a single RGB input through the supervision of easily  ...  We present a method for reconstructing accurate and consistent 3D hands from a monocular video.  ...  Motion Learning from Sequence Data for 3D Hand Estimation.  ... 
arXiv:2201.09548v1 fatcat:sv6463vtzndkdlv2jhsq2itpim

Recent Advances of Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective

Wu Liu, Tao Mei
2022 ACM Computing Surveys  
Recently, benefiting from the deep learning technologies, a significant amount of research efforts have advanced the monocular human pose estimation both in 2D and 3D areas.  ...  Especially, we provide insightful analyses for the intrinsic connections and methods evolution from 2D to 3D pose estimation.  ...  It is further applied to video pose estimation by searching for the temporal feature fusion and automatic computation allocation in videos.  ... 
doi:10.1145/3524497 fatcat:4pbvntngrnfp7lqhcpjmy7p2fq

Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective [article]

Wu Liu, Qian Bao, Yu Sun, Tao Mei
2021 arXiv   pre-print
Recently, benefited from the deep learning technologies, a significant amount of research efforts have greatly advanced the monocular human pose estimation both in 2D and 3D areas.  ...  Estimation of the human pose from a monocular camera has been an emerging research topic in the computer vision community with many applications.  ...  Embedding [42] . 1) Single Person Pose Estimation in Videos: For single person pose estimation in videos, most works explore to propagate temporal clues across frames for refining the single frame pose  ... 
arXiv:2104.11536v1 fatcat:tdag2jq2vjdrjekwukm5nu7l6a

Appearance Consensus Driven Self-Supervised Human Mesh Recovery [article]

Jogendra Nath Kundu, Mugalodi Rakesh, Varun Jampani, Rahul Mysore Venkatesh, R. Venkatesh Babu
2020 arXiv   pre-print
We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images in the absence of any paired supervision.  ...  We achieve state-of-the-art results on the standard model-based 3D pose estimation benchmarks at comparable supervision levels.  ...  Self-supervised learning objectives For a given image pair, denoted as I a and I b (depicting the same person in diverse pose and BGs), we forward them through two parallel pathways of our colored mesh  ... 
arXiv:2008.01341v1 fatcat:jyqhw3pwjrcxxpozwetd36r6ay

SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition [article]

Hezhen Hu, Weichao Zhao, Wengang Zhou, Yuechen Wang, Houqiang Li
2021 arXiv   pre-print
In this paper, we introduce the first self-supervised pre-trainable SignBERT with incorporated hand prior for SLR.  ...  SignBERT views the hand pose as a visual token, which is derived from an off-the-shelf pose extractor. The visual tokens are then embedded with gesture state, temporal and hand chirality information.  ...  This work was supported in part by the National Natural Science Foundation of China under Contract U20A20183, 61632019, and 62021001, and in part by the Youth Innovation Promotion Association CAS under  ... 
arXiv:2110.05382v1 fatcat:dnetyrcjbfccvkgruc2bdqz3ha

3D Human Pose, Shape and Texture from Low-Resolution Images and Videos [article]

Xiangyu Xu, Hao Chen, Francesc Moreno-Noguer, Laszlo A. Jeni, Fernando De la Torre
2021 arXiv   pre-print
3D human pose and shape estimation from monocular images has been an active research area in computer vision.  ...  To address the above issues, this paper proposes a novel algorithm called RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme.  ...  Self-Supervised Loss The 3D human pose and shape estimation is usually posed as a weakly-supervised problem as only a small part of the training data has 3D labels, and this is especially the case for  ... 
arXiv:2103.06498v1 fatcat:ridse54hh5hqhmfcs44ytnsutm

Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction [article]

Mengshi Qi, Edoardo Remelli, Mathieu Salzmann, Pascal Fua
2020 arXiv   pre-print
Deep learning-solutions for hand-object 3D pose and shape estimation are now very effective when an annotated dataset is available to train them to handle the scenarios and lighting conditions they will  ...  temporal consistency to fine-tune the domain-adapted model in a self-supervised fashion.  ...  Yao, “Self-Supervised 3D tion Using Egocentric Workspaces,” in Conference on Computer Vision Hand Pose Estimation Through Training by Fitting,” in Conference and Pattern  ... 
arXiv:2012.11260v1 fatcat:wzloca4avzbtfcumf26bek6dc4

Deep Learning-Based Human Pose Estimation: A Survey [article]

Ce Zheng and Wenhan Wu and Chen Chen and Taojiannan Yang and Sijie Zhu and Ju Shen and Nasser Kehtarnavaz and Mubarak Shah
2022 arXiv   pre-print
The goal of this survey paper is to provide a comprehensive review of recent deep learning-based solutions for both 2D and 3D pose estimation via a systematic analysis and comparison of these solutions  ...  More than 250 research papers since 2014 are covered in this survey. Furthermore, 2D and 3D human pose estimation datasets and evaluation metrics are included.  ...  [262] introduced the contrastive learning scheme into self-supervised resolution-aware SMPL-based network.  ... 
arXiv:2012.13392v4 fatcat:ypnqtq3sbncr5fuujif2dhqwji

Deep Learning Methods for 3D Human Pose Estimation under Different Supervision Paradigms: A Survey

Dejun Zhang, Yiqi Wu, Mingyue Guo, Yilin Chen
2021 Electronics  
Based on this literature survey, it can be concluded that each branch of 3D human pose estimation starts with fully-supervised methods, and there is still much room for multi-person pose estimation based  ...  Moreover, due to the significance of data for learning-based methods, this paper surveys the 3D human pose estimation methods according to the taxonomy of supervision form.  ...  [71] introduce a temporal motion model for 3D human pose estimation from videos.  ... 
doi:10.3390/electronics10182267 fatcat:ajnizu776ncpto3jvyh3zye2si

3D Human Pose Machines with Self-supervised Learning [article]

Keze Wang and Liang Lin and Chenhan Jiang and Chen Qian and Pengxu Wei
2019 arXiv   pre-print
of "free" self-supervision for accurate 3D human pose estimation.  ...  Specifically, the proposed mechanism involves two dual learning tasks, i.e., the 2D-to-3D pose transformation and 3D-to-2D pose projection, to serve as a bridge between 3D and 2D human poses in a type  ...  Self-supervised Learning.  ... 
arXiv:1901.03798v2 fatcat:kmthep6qnnbbzlxrhmnwgqy264

Anatomy-aware 3D Human Pose Estimation with Bone-based Pose Decomposition [article]

Tianlang Chen, Chen Fang, Xiaohui Shen, Yiheng Zhu, Zhili Chen, Jiebo Luo
2021 arXiv   pre-print
In this work, we propose a new solution to 3D human pose estimation in videos.  ...  This promotes us to develop effective techniques to utilize global information across all the frames in a video for high-accuracy bone length prediction.  ...  [4] present a weakly-supervised method of learning a geometry-aware representation to bridge multi-view images for pose estimation.  ... 
arXiv:2002.10322v5 fatcat:bkd22b5u7raevef7t6pqcihcmm

Recovering 3D Human Mesh from Monocular Images: A Survey [article]

Yating Tian, Hongwen Zhang, Yebin Liu, Limin Wang
2022 arXiv   pre-print
Estimating human pose and shape from monocular images is a long-standing problem in computer vision.  ...  Meanwhile, continuous efforts are devoted to improving the quality of 3D mesh labels for a wide range of datasets.  ...  Both datasets contain synchronized video from multiple camera views and associated 3D pose ground truth. Human3.6M [85] is a benchmark dataset for 3D pose estimation.  ... 
arXiv:2203.01923v2 fatcat:vb6xa5wdsrhdxd2ebvg54qq2m4

Learning 3D Human Pose from Structure and Motion [chapter]

Rishabh Dabral, Anurag Mundhada, Uday Kusupati, Safeer Afaque, Abhishek Sharma, Arjun Jain
2018 Lecture Notes in Computer Science  
3D human pose estimation from a single image is a challenging problem, especially for in-the-wild settings due to the lack of 3D annotated data.  ...  We also present a simple temporal network that exploits temporal and structural cues present in predicted pose sequences to temporally harmonize the pose estimations.  ...  We also present a simple learnable temporal pose model for pose-estimation from videos.  ... 
doi:10.1007/978-3-030-01240-3_41 fatcat:xqqmmqwhjvb73pmnr7sf6qxh2e
« Previous Showing results 1 — 15 out of 1,035 results