Zobrazeno 1 - 10
of 97
pro vyhledávání: '"Fangyin Wei"'
Publikováno v:
ACM Transactions on Graphics. 39:1-18
Objects obscured by occluders are considered lost in the images acquired by conventional camera systems, prohibiting both visualization and understanding of such hidden objects. Non-line-of-sight methods (NLOS) aim at recovering information about hid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c4f14ade8a2872478b47dfe0c57cfb37
https://doi.org/10.1145/3414685.3417825
https://doi.org/10.1145/3414685.3417825
Autor:
Fangyin Wei, Rohan Chabra, Lingni Ma, Christoph Lassner, Michael Zollhoefer, Szymon Rusinkiewicz, Chris Sweeney, Richard Newcombe, Mira Slavcheva
Learning geometry, motion, and appearance priors of object classes is important for the solution of a large variety of computer vision problems. While the majority of approaches has focused on static objects, dynamic objects, especially with controll
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::599fc14e07ea10319337d548375edbb5
Publikováno v:
3DV
Many applications in 3D shape design and augmentation require the ability to make specific edits to an object's semantic parameters (e.g., the pose of a person's arm or the length of an airplane's wing) while preserving as much existing details as po
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1980370db086340bfe7a8647cd3b7209
https://doi.org/10.1109/3dv50981.2020.00053
https://doi.org/10.1109/3dv50981.2020.00053
Autor:
Fahim Mannan, Jürgen Dickmann, Felix Heide, Nicolas Scheiner, Nils Appenrodt, Buu Phan, Fangyin Wei, Klaus Dietmayer, Werner Ritter, Florian Kraus, Bernhard Sick
Publikováno v:
CVPR
Conventional sensor systems record information about directly visible objects, whereas occluded scene components are considered lost in the measurement process. Non-line-of-sight (NLOS) methods try to recover such hidden objects from their indirect r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::051b4ba5eb3d34468ecd41d428fc10ed
http://arxiv.org/abs/1912.06613
http://arxiv.org/abs/1912.06613
Despite the recent success of deep learning models in numerous applications, their widespread use on mobile devices is seriously impeded by storage and computational requirements. In this paper, we propose a novel network compression method called Ad
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bfd633ca7bc5afae52ce8b950d4aaac4
http://arxiv.org/abs/1906.07671
http://arxiv.org/abs/1906.07671
Publikováno v:
CVPR
This paper proposes learning disentangled but complementary face features with minimal supervision by face identification. Specifically, we construct an identity Distilling and Dispelling Autoencoder (D2AE) framework that adversarially learns the ide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::292b31b65d881ae07b75729214d17c78
https://doi.org/10.1109/cvpr.2018.00222
https://doi.org/10.1109/cvpr.2018.00222
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012304
ECCV (6)
ECCV (6)
State-of-the-art human pose estimation methods are based on heat map representation. In spite of the good performance, the representation has a few issues in nature, such as non-differentiable post-processing and quantization error. This work shows t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::96fd931f9b995f51ed1b73408bae7e56
https://doi.org/10.1007/978-3-030-01231-1_33
https://doi.org/10.1007/978-3-030-01231-1_33
Publikováno v:
ICCV
Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multi-scale object detection, which has the bottleneck of computational cost in practice.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::575a4176e42cff76c5080ee08ad04d08
http://arxiv.org/abs/1707.09531
http://arxiv.org/abs/1707.09531
Publikováno v:
ACM Transactions on Graphics; Oct2024, Vol. 43 Issue 5, p1-12, 12p
Autor:
Zuo, Ronglai, Mak, Brian
Publikováno v:
ACM Transactions on Multimedia Computing, Communications & Applications; Jun2024, Vol. 20 Issue 6, p1-25, 25p