Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation

Autor: Zicong Fan, Adrian Spurr, Muhammed Kocabas, Siyu Tang, Michael J. Black, Otmar Hilliges

Publikováno v: 2021 International Conference on 3D Vision (3DV 2021)
2021 International Conference on 3D Vision (3DV)

In natural conversation and interaction, our hands often overlap or are in contact with each other. Due to the homogeneous appearance of hands, this makes estimating the 3D pose of interacting hands from images difficult. In this paper we demonstrate

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b5111d07592b381d3a13d031c516e059
http://arxiv.org/abs/2107.00434

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

Autor: Shreyas Hampali, Fu Xiong, Shipeng Xie, Zdenek Krnoul, Weiguo Zhou, Sijia Mei, Seungryul Baek, Zhaohui Zhang, Haifeng Sun, Guillermo Garcia-Hernando, Yang Xiao, Dongheui Lee, Angela Yao, Umar Iqbal, Mahdi Rad, Marek Hrúz, Adrian Spurr, Qingfu Wan, Zhiguo Cao, Junsong Yuan, Vincent Lepetit, Pavlo Molchanov, Romain Brégier, Pengfei Ren, Yunhui Liu, Shile Li, Philippe Weinzaepfel, Linlin Yang, Anil Armagan, Weiting Huang, Grégory Rogez, Boshen Zhang, Tae-Kyun Kim, Mingxiu Chen, Jakub Kanis

Publikováno v: Computer Vision – ECCV 2020 ISBN: 9783030585914
ECCV (23)

We study how well different types of approaches generalise in the task of 3D hand pose estimation under single hand scenarios and hand-object interaction. We show that the accuracy of state-of-the-art methods can drop, and that they fail mostly on po

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::334571a0b2fa3856d677209cb23e6322

Cross-Modal Deep Variational Hand Pose Estimation

Autor: Jie Song, Otmar Hilliges, Seonwook Park, Adrian Spurr

Publikováno v: CVPR
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

The human hand moves in complex and high-dimensional ways, making estimation of 3D hand pose configurations from images alone a challenging task. In this work we propose a method to learn a statistical hand model represented by a cross-modal trained

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4ab5b8e26ce338c89f601e7741f1c709
https://doi.org/10.1109/cvpr.2018.00017

Guiding InfoGAN with Semi-supervision

Autor: Otmar Hilliges, Adrian Spurr, Emre Aksan

Publikováno v: Machine Learning and Knowledge Discovery in Databases ISBN: 9783319712482
ECML/PKDD (1)
Proceedings of Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2017
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Machine Learning and Knowledge Discovery in Databases

In this paper we propose a new semi-supervised GAN architecture (ss-InfoGAN) for image synthesis that leverages information from few labels (as little as \(0.22\%\), max. \(10\%\) of the dataset) to learn semantically meaningful and controllable data

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bfea107521d6dc902338095f7701a16e
https://doi.org/10.1007/978-3-319-71249-9_8