17.3.1 Opeical Flow, Learning, Neural Networks, GAN

Chapter Contents (Back)
Optical Flow. Learning. Neural Networks. GAN.

Chen, T.W.[Tsu Wang], and Lin, W.C.[Wei Chung], Chen, C.T.,
Artificial Neural Networks for 3-D Motion Analysis I: Rigid Motion,
TNN(6), No. 6, November 1995, pp. 1386-1393. BibRef 9511
And:
Artificial Neural Networks for 3-D Motion Analysis II: Nonrigid Motion,
TNN(6), No. 6, November 1995, pp. 1394-1401.
See also Neural-Network Approach to CSG-Based 3-D Object Recognition, A. BibRef

Wang, R.Y.,
A Network Model for the Optic Flow Computation of the MST Neurons,
NeurNet(9), No. 3, April 1996, pp. 411-426. 9605
BibRef

Gray, W.S., Nabet, B.,
Volterra Series Analysis and Synthesis of a Neural Network for Velocity Estimation,
SMC-B(29), No. 2, April 1999, pp. 190. BibRef 9904

Mayer, N.[Nikolaus], Ilg, E.[Eddy], Fischer, P.[Philipp], Hazirbas, C.[Caner], Cremers, D.[Daniel], Dosovitskiy, A.[Alexey], Brox, T.[Thomas],
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?,
IJCV(126), No. 9, September 2018, pp. 942-960.
Springer DOI 1809
BibRef

Dosovitskiy, A., Fischery, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., van de Smagt, P., Cremers, D., Brox, T.,
FlowNet: Learning Optical Flow with Convolutional Networks,
ICCV15(2758-2766)
IEEE DOI 1602
Computer architecture BibRef

Ilg, E.[Eddy], Saikia, T.[Tonmoy], Keuper, M.[Margret], Brox, T.[Thomas],
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation,
ECCV18(XII: 626-643).
Springer DOI 1810
BibRef

Ilg, E.[Eddy], Mayer, N.[Nikolaus], Saikia, T.[Tonmoy], Keuper, M.[Margret], Dosovitskiy, A.[Alexey], Brox, T.[Thomas],
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks,
CVPR17(1647-1655)
IEEE DOI 1711
Adaptive optics, Computer architecture, Estimation, Optical imaging, Schedules, Stacking, Training BibRef

Wannenwetsch, A.S., Keuper, M., Roth, S.,
ProbFlow: Joint Optical Flow and Uncertainty Estimation,
ICCV17(1182-1191)
IEEE DOI 1802
Bayes methods, entropy, image sequences, motion estimation, energy minimization approach, energy-based formulations, Uncertainty BibRef

Makansi, O.[Osama], Ilg, E.[Eddy], Cicek, O.[Ozgun], Brox, T.[Thomas],
Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction,
CVPR19(7137-7146).
IEEE DOI 2002
BibRef

Ilg, E.[Eddy], Çiçek, Ö.[Özgün], Galesso, S.[Silvio], Klein, A.[Aaron], Makansi, O.[Osama], Hutter, F.[Frank], Brox, T.[Thomas],
Uncertainty Estimates and Multi-hypotheses Networks for Optical Flow,
ECCV18(VII: 677-693).
Springer DOI 1810
BibRef

Paredes-Vallés, F.[Federico], Scheper, K.Y.W.[Kirk Y. W.], de Croon, G.C.H.E.[Guido C.H.E.],
Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception,
PAMI(42), No. 8, August 2020, pp. 2051-2064.
IEEE DOI 2007
Neurons, Visualization, Biomedical optical imaging, Optical sensors, Biological system modeling, unsupervised learning BibRef

Hui, T.W.[Tak-Wai], Tang, X.[Xiaoou], Loy, C.C.[Chen Change],
A Lightweight Optical Flow CNN: Revisiting Data Fidelity and Regularization,
PAMI(43), No. 8, August 2021, pp. 2555-2569.
IEEE DOI 2107
BibRef
Earlier:
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation,
CVPR18(8981-8989)
IEEE DOI 1812
Optical imaging, Adaptive optics, Estimation, Optical computing, Convolutional codes, Optical network units, and warping. Estimation, Feature extraction, Convolution, Optical filters, Optical fiber networks BibRef

Hui, T.W.[Tak-Wai], Loy, C.C.[Chen Change],
LiteFlownet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation,
ECCV20(XX:169-184).
Springer DOI 2011
BibRef

Che, T.T.[Tong-Tong], Zheng, Y.J.[Yuan-Jie], Yang, Y.S.[Yun-Shuai], Hou, S.J.[Su-Juan], Jia, W.K.[Wei-Kuan], Yang, J.[Jie], Gong, C.[Chen],
SDOF-GAN: Symmetric Dense Optical Flow Estimation With Generative Adversarial Networks,
IP(30), 2021, pp. 6036-6049.
IEEE DOI 2107
Estimation, Optical imaging, Adaptive optics, Generative adversarial networks, Brightness, semi-supervised learning BibRef

Liu, S.C.[Shuai-Cheng], Luo, K.M.[Kun-Ming], Ye, N.J.[Nian-Jin], Wang, C.[Chuan], Wang, J.[Jue], Zeng, B.[Bing],
OIFlow: Occlusion-Inpainting Optical Flow Estimation by Unsupervised Learning,
IP(30), 2021, pp. 6420-6433.
IEEE DOI 2107
Optical imaging, Feature extraction, Optical variables control, Estimation, Optical fiber networks, Adaptive optics, unsupervised learning BibRef


Artizzu, C.O.[Charles-Olivier], Zhang, H.[Haozhou], Allibert, G.[Guillaume], Demonceaux, C.[Cédric],
OmniFlowNet: a Perspective Neural Network Adaptation for Optical Flow Estimation in Omnidirectional Images,
ICPR21(2657-2662)
IEEE DOI 2105
Training, Convolution, Image processing, Neural networks, Estimation, Optical distortion, Distortion BibRef

Yu, S.J.[Suihan-Jin], Zhang, Y.M.[You-Min], Wang, C.[Chen], Bai, X.[Xiao], Zhang, L.[Liang], Hancock, E.R.[Edwin R.],
HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects,
ICPR21(1197-1204)
IEEE DOI 2105
Image resolution, Estimation, Search problems, Pattern recognition, Task analysis, Optical flow BibRef

Li, Z.Y.[Zhuo-Yan], Shen, J.W.[Jia-Wei], Liu, R.[Ruitao],
A Lightweight Network to Learn Optical Flow from Event Data,
ICPR21(1-7)
IEEE DOI 2105
Image motion analysis, Laplace equations, Data integrity, Neural networks, Estimation, Computer architecture, CNN BibRef

Lee, C.[Chankyu], Kosta, A.K.[Adarsh Kumar], Zhu, A.Z.[Alex Zihao], Chaney, K.[Kenneth], Daniilidis, K.[Kostas], Roy, K.[Kaushik],
Spike-flownet: Event-based Optical Flow Estimation with Energy-efficient Hybrid Neural Networks,
ECCV20(XXIX: 366-382).
Springer DOI 2010
BibRef

Xie, S., Lai, P.K., Laganiere, R., Lang, J.,
Effective Convolutional Neural Network Layers in Flow Estimation for Omni-Directional Images,
3DV19(671-680)
IEEE DOI 1911
Estimation, Optical imaging, Convolution, Optical computing, Adaptive optics, Optical fiber networks, Neural networks, neural network BibRef

Lu, Y.[Yao], Valmadre, J.[Jack], Wang, H.[Heng], Kannala, J.H.[Ju-Ho], Harandi, M.[Mehrtash], Torr, P.H.S.[Philip H. S.],
Devon: Deformable Volume Network for Learning Optical Flow,
WACV20(2694-2702)
IEEE DOI 2006
BibRef
Earlier: OpticalFlow18(VI:673-677).
Springer DOI 1905
Optical imaging, Optical computing, Optical distortion, Neural networks, Optical fiber networks, Optical propagation, Estimation BibRef

Yang, Y.C.[Yan-Chao], Soatto, S.[Stefano],
Conditional Prior Networks for Optical Flow,
ECCV18(XV: 282-298).
Springer DOI 1810
BibRef

Chapter on Optical Flow Field Computations and Use continues in
Scene Flow, Depth Image Flow, RGB-D .


Last update:Nov 1, 2021 at 09:26:50