Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Can Pu"'
Publikováno v:
Remote Sensing, Vol 11, Iss 5, p 487 (2019)
Refining raw disparity maps from different algorithms to exploit their complementary advantages is still challenging. Uncertainty estimation and complex disparity relationships among pixels limit the accuracy and robustness of existing methods and th
Externí odkaz:
https://doaj.org/article/1873836c1b4549a1bcec458c3440f245
Publikováno v:
ICRA
This paper presents a novel non-Gaussian inference algorithm, Normalizing Flow iSAM (NF-iSAM), for solving SLAM problems with non-Gaussian factors and/or non-linear measurement models. NF-iSAM exploits the expressive power of neural networks, and tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c62ddb638fad294fd451835f3bcbc84
http://arxiv.org/abs/2105.05045
http://arxiv.org/abs/2105.05045
Autor:
Qiangqiang Huang, Can Pu, Kasra Khosoussi, David M. Rosen, Dehann Fourie, Jonathan P. How, John J. Leonard
This paper presents normalizing flows for incremental smoothing and mapping (NF-iSAM), a novel algorithm for inferring the full posterior distribution in SLAM problems with nonlinear measurement models and non-Gaussian factors. NF-iSAM exploits the e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82aa8af9e8fb1bac9c31b5ab7c0abe6d
Autor:
Can Pu, Ryan G. McClarren
Publikováno v:
Journal of Computational and Theoretical Transport. 46:366-378
In this work, we extend the solid harmonics derivation, which was used by Ackroyd et al to derive the steady-state SP$_N$ equations, to transient problems. The derivation expands the angular flux in ordinary surface harmonics but uses harmonic polyno
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53023afa94e816668edb92181ff1dfc0
https://doi.org/10.1080/23324309.2017.1352516
https://doi.org/10.1080/23324309.2017.1352516
Autor:
Robert B. Fisher, Can Pu
Publikováno v:
ICIP
Pu, C & Fisher, R 2019, UDFNet: Unsupervised Disparity Fusion with Adversarial Networks . in 2019 26th IEEE International Conference on Image Processing (ICIP) . Institute of Electrical and Electronics Engineers (IEEE), pp. 1765-1769, 26th IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, Province of China, 22/09/19 . https://doi.org/10.1109/ICIP.2019.8803180
Pu, C & Fisher, R 2019, UDFNet: Unsupervised Disparity Fusion with Adversarial Networks . in 2019 26th IEEE International Conference on Image Processing (ICIP) . Institute of Electrical and Electronics Engineers (IEEE), pp. 1765-1769, 26th IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, Province of China, 22/09/19 . https://doi.org/10.1109/ICIP.2019.8803180
Existing disparity fusion methods based on deep learning achieve state-of-the-art performance, but they require ground truth disparity data to train. As far as I know, this is the first time an unsupervised disparity fusion not using ground truth dis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e00a30a10e6ec5816db0a955b1748091
http://arxiv.org/abs/1904.10044
http://arxiv.org/abs/1904.10044
Publikováno v:
International Journal of Innovation, Management and Technology. 6:278-284
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea520fe63c0b5e4c199cf33c0f002331
https://doi.org/10.7763/ijimt.2015.v6.615
https://doi.org/10.7763/ijimt.2015.v6.615
Publikováno v:
Pu, C, Song, R, Tylecek, R, Li, N & Fisher, R 2019, ' SDF-MAN: Semi-supervised Disparity Fusion with Multi-scale Adversarial Networks ', Remote Sensing, vol. 11, no. 5, 487 . https://doi.org/10.3390/rs11050487
Remote Sensing; Volume 11; Issue 5; Pages: 487
Remote Sensing, Vol 11, Iss 5, p 487 (2019)
Remote Sensing; Volume 11; Issue 5; Pages: 487
Remote Sensing, Vol 11, Iss 5, p 487 (2019)
Refining raw disparity maps from different algorithms to exploit their complementary advantages is still challenging. Uncertainty estimation and complex disparity relationships among pixels limit the accuracy and robustness of existing methods and th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5422184b366bcfccf0b3192bb3d33f06
https://doi.org/10.3390/rs11050487
https://doi.org/10.3390/rs11050487