Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Zhoutong Zhang"'
Publikováno v:
ACM Transactions on Graphics. 40:1-12
We present a method to estimate depth of a dynamic scene, containing arbitrary moving objects, from an ordinary video captured with a moving camera. We seek a geometrically and temporally consistent solution to this underconstrained problem: the dept
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9e0ad81af61d2d324fb52758562329f
https://doi.org/10.1145/3476576.3476728
https://doi.org/10.1145/3476576.3476728
Autor:
Zhoutong Zhang, Forrester Cole, Zhengqi Li, Michael Rubinstein, Noah Snavely, William T. Freeman
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198267
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de4b3f753e7be9fb5979a59d6ea780ca
https://doi.org/10.1007/978-3-031-19827-4_2
https://doi.org/10.1007/978-3-031-19827-4_2
Publikováno v:
CVPR
We propose an end-to-end variational generative model for scene layout synthesis conditioned on scene graphs. Unlike unconditional scene layout generation, we use scene graphs as an abstract but general representation to guide the synthesis of divers
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9772a16b0953bb4bbd05cf9a9dec6a30
http://arxiv.org/abs/2007.11744
http://arxiv.org/abs/2007.11744
Publikováno v:
2019 Conference on Cognitive Computational Neuroscience.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bbba02430472732f2e878e234cee710a
https://doi.org/10.32470/ccn.2019.1276-0
https://doi.org/10.32470/ccn.2019.1276-0
Autor:
Joshua B. Tenenbaum, Xingyuan Sun, Tianfan Xue, Jiajun Wu, William T. Freeman, Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang
Publikováno v:
CVPR
MIT web domain
MIT web domain
We study 3D shape modeling from a single image and make contributions to it in three aspects. First, we present Pix3D, a large-scale benchmark of diverse image-shape pairs with pixel-level 2D-3D alignment. Pix3D has wide applications in shape-related
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f39dc79b772dcc4e53846c019a603933
Autor:
Joshua B. Tenenbaum, Zhoutong Zhang, Jiajun Wu, Chengkai Zhang, William T. Freeman, Xiuming Zhang
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012519
ECCV (11)
ECCV (11)
The problem of single-view 3D shape completion or reconstruction is challenging, because among the many possible shapes that explain an observation, most are implausible and do not correspond to natural objects. Recent research in the field has tackl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::42ddf917a8643070d4012aaf774d2d7c
https://doi.org/10.1007/978-3-030-01252-6_40
https://doi.org/10.1007/978-3-030-01252-6_40
Autor:
William T. Freeman, Jiajun Wu, Chengkai Zhang, Tianfan Xue, Zhoutong Zhang, Joshua B. Tenenbaum
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012397
ECCV (9)
ECCV (9)
Humans recognize object structure from both their appearance and motion; often, motion helps to resolve ambiguities in object structure that arise when we observe object appearance only. There are particular scenarios, however, where neither appearan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d6634701c3d1e3cfc6b203003144aa49
https://doi.org/10.1007/978-3-030-01240-3_46
https://doi.org/10.1007/978-3-030-01240-3_46
Autor:
Qiujia Li, Zhoutong Zhang, Josh H. McDermott, James Traer, Jiajun Wu, Joshua B. Tenenbaum, Zhengjia Huang, William T. Freeman
Publikováno v:
MIT web domain
ICCV
ICCV
© 2017 IEEE. Humans infer rich knowledge of objects from both auditory and visual cues. Building a machine of such competency, however, is very challenging, due to the great difficulty in capturing large-scale, clean data of objects with both their
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ac2f25a2eaf0cbbe5ed87601dea9eaed
https://hdl.handle.net/1721.1/137459
https://hdl.handle.net/1721.1/137459
Publikováno v:
CVPR
We present a novel phase-based approach for reconstructing 4D light field from a micro-baseline stereo pair. Our approach takes advantage of the unique property of complex steerable pyramid filters in micro-baseline stereo. We first introduce a Dispa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0dec170b5ae02f192889dddfed7222ce
https://doi.org/10.1109/cvpr.2015.7299004
https://doi.org/10.1109/cvpr.2015.7299004