Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Tai-Pang Wu"'
Publikováno v:
IJCNN
Deep metric learning methods are quite effective in exploring discriminative feature embeddings, among which triplet loss and its variants are widely utilized. However, in existing methods, the tightness information for intra-class samples is ignored
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::10ebee81b5af10da86d97ca0875f9307
https://doi.org/10.1109/ijcnn.2019.8851996
https://doi.org/10.1109/ijcnn.2019.8851996
Publikováno v:
VCIP
To learn the optimal similarity function between probe and gallery images in Person re-identification, effective deep metric learning methods have been extensively explored to obtain discriminative feature embedding. However, existing metric loss lik
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::305667756e5b6e987b02d5ba50acbf04
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 37:890-897
Reconstructing transparent objects is a challenging problem. While producing reasonable results for quite complex objects, existing approaches require custom calibration or somewhat expensive labor to achieve high precision. When an overall shape pre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec53078b1f567d82c919af3178e0284e
https://doi.org/10.1109/tpami.2014.2346195
https://doi.org/10.1109/tpami.2014.2346195
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 32:2085-2099
Representative surface reconstruction algorithms taking a gradient field as input enforce the integrability constraint in a discrete manner. While enforcing integrability allows the subsequent integration to produce surface heights, existing algorith
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6415236e90d9011ff3bde25168aff455
https://doi.org/10.1109/tpami.2009.183
https://doi.org/10.1109/tpami.2009.183
Publikováno v:
ACM Transactions on Graphics. 29:1-15
This article introduces an optimization approach for modeling and rendering impossible figures. Our solution is inspired by how modeling artists construct physical 3D models to produce a valid 2D view of an impossible figure. Given a set of 3D locall
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7b6ca1b31d463fe8cacb7d07e44014bc
https://doi.org/10.1145/1731047.1731051
https://doi.org/10.1145/1731047.1731051
Autor:
Chi-Keung Tang, Tai-Pang Wu
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 32:546-560
This paper presents a robust and automatic approach to photometric stereo, where the two main components, namely surface normals and visible surfaces, are respectively optimized by Expectation Maximization (EM). A dense set of input images is conveni
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9040a81105fb396397a479733f4b00e2
https://doi.org/10.1109/tpami.2009.15
https://doi.org/10.1109/tpami.2009.15
Publikováno v:
WACV
Conventional photometric stereo requires to capture images or videos in a dark room to obstruct complex environment light as much as possible. This paper presents a new method that capitalizes on environment light to avail geometry reconstruction, th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c74d6e1941f5827ba59140555b75e725
https://doi.org/10.1109/wacv.2015.47
https://doi.org/10.1109/wacv.2015.47
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 28:1830-1846
We address the problem of robust normal reconstruction by dense photometric stereo, in the presence of complex geometry, shadows, highlight, transparencies, variable attenuation in light intensities, and inaccurate estimation in light directions. The
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d8dcdf8e436b914185455e9812ff6d23
https://doi.org/10.1109/tpami.2006.224
https://doi.org/10.1109/tpami.2006.224
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 28:832-839
This paper presents a complete system capable of synthesizing a large number of pixels that are missing due to occlusion or damage in an uncalibrated input video. These missing pixels may correspond to the static background or cyclic motions of the c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0798b2a9e6730426fb75f98a2ee24238
https://doi.org/10.1109/tpami.2006.108
https://doi.org/10.1109/tpami.2006.108