The Experts below are selected from a list of 78267 Experts worldwide ranked by ideXlab platform
Gerard Medioni - One of the best experts on this subject based on the ideXlab platform.
-
a Closed Form Solution to tensor voting theory and applications
arXiv: Computer Vision and Pattern Recognition, 2016Co-Authors: Saikit Yeung, Jiaya Jia, Chikeung Tang, Gerard MedioniAbstract:We prove a Closed-Form Solution to tensor voting (CFTV): given a point set in any dimensions, our Closed-Form Solution provides an exact, continuous and efficient algorithm for computing a structure-aware tensor that simultaneously achieves salient structure detection and outlier attenuation. Using CFTV, we prove the convergence of tensor voting on a Markov random field (MRF), thus termed as MRFTV, where the structure-aware tensor at each input site reaches a stationary state upon convergence in structure propagation. We then embed structure-aware tensor into expectation maximization (EM) for optimizing a single linear structure to achieve efficient and robust parameter estimation. Specifically, our EMTV algorithm optimizes both the tensor and fitting parameters and does not require random sampling consensus typically used in existing robust statistical techniques. We perFormed quantitative evaluation on its accuracy and robustness, showing that EMTV perForms better than the original TV and other state-of-the-art techniques in fundamental matrix estimation for multiview stereo matching. The extensions of CFTV and EMTV for extracting multiple and nonlinear structures are underway. An addendum is included in this arXiv version.
-
a Closed Form Solution to tensor voting theory and applications
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012Co-Authors: Saikit Yeung, Jiaya Jia, Chikeung Tang, Gerard MedioniAbstract:We prove a Closed-Form Solution to tensor voting (CFTV): Given a point set in any dimensions, our Closed-Form Solution provides an exact, continuous, and efficient algorithm for computing a structure-aware tensor that simultaneously achieves salient structure detection and outlier attenuation. Using CFTV, we prove the convergence of tensor voting on a Markov random field (MRF), thus termed as MRFTV, where the structure-aware tensor at each input site reaches a stationary state upon convergence in structure propagation. We then embed structure-aware tensor into expectation maximization (EM) for optimizing a single linear structure to achieve efficient and robust parameter estimation. Specifically, our EMTV algorithm optimizes both the tensor and fitting parameters and does not require random sampling consensus typically used in existing robust statistical techniques. We perFormed quantitative evaluation on its accuracy and robustness, showing that EMTV perForms better than the original TV and other state-of-the-art techniques in fundamental matrix estimation for multiview stereo matching. The extensions of CFTV and EMTV for extracting multiple and nonlinear structures are underway.
Trungkien Le - One of the best experts on this subject based on the ideXlab platform.
-
Closed Form Solution for tdoa based joint source and sensor localization in two dimensional space
European Signal Processing Conference, 2016Co-Authors: Trungkien LeAbstract:In this paper, we propose a Closed-Form Solution for time-difference-of-arrival (TDOA) based joint source and sensor localization in two-dimensional space (2D). This Closed-Form Solution is a combination of two Closed-Form Solutions for time-of-arrival inFormation recovery and time-of-arrival (TOA)-based joint source and sensor localization in 2D. In our previous works, we derived Closed-Form Solutions for TOA-based joint source and sensor localization and near-Closed-Form Solutions for TOA inFormation recovery in three-dimensional space (3D). Since the localization in 2D is simpler than that in 3D, Closed-Form Solutions for both problems in 2D are derived in this paper. The root-mean-square errors (RMSEs) achieved by the proposed Closed-Form Solution are compared with the Cramer-Rao lower bound (CRLB) in synthetic experiments. The results show that the proposed Solution works well in both low-noise and noisy cases and with both small and large numbers of sources and sensors.
Nobutaka Ono - One of the best experts on this subject based on the ideXlab platform.
-
EUSIPCO - Closed-Form Solution for TDOA-based joint source and sensor localization in two-dimensional space
2016 24th European Signal Processing Conference (EUSIPCO), 2016Co-Authors: Nobutaka OnoAbstract:In this paper, we propose a Closed-Form Solution for time-difference-of-arrival (TDOA) based joint source and sensor localization in two-dimensional space (2D). This Closed-Form Solution is a combination of two Closed-Form Solutions for time-of-arrival inFormation recovery and time-of-arrival (TOA)-based joint source and sensor localization in 2D. In our previous works, we derived Closed-Form Solutions for TOA-based joint source and sensor localization and near-Closed-Form Solutions for TOA inFormation recovery in three-dimensional space (3D). Since the localization in 2D is simpler than that in 3D, Closed-Form Solutions for both problems in 2D are derived in this paper. The root-mean-square errors (RMSEs) achieved by the proposed Closed-Form Solution are compared with the Cramer-Rao lower bound (CRLB) in synthetic experiments. The results show that the proposed Solution works well in both low-noise and noisy cases and with both small and large numbers of sources and sensors.
Li Zhang - One of the best experts on this subject based on the ideXlab platform.
-
a Closed Form Solution to universal style transfer
International Conference on Computer Vision, 2019Co-Authors: Hao Zhao, Anbang Yao, Yurong Chen, Li ZhangAbstract:Universal style transfer tries to explicitly minimize the losses in feature space, thus it does not require training on any pre-defined styles. It usually uses different layers of VGG network as the encoders and trains several decoders to invert the features into images. Therefore, the effect of style transfer is achieved by feature transForm. Although plenty of methods have been proposed, a theoretical analysis of feature transForm is still missing. In this paper, we first propose a novel interpretation by treating it as the optimal transport problem. Then, we demonstrate the relations of our Formulation with Former works like Adaptive Instance Normalization (AdaIN) and Whitening and Coloring TransForm (WCT). Finally, we derive a Closed-Form Solution named Optimal Style Transfer (OST) under our Formulation by additionally considering the content loss of Gatys. Comparatively, our Solution can preserve better structure and achieve visually pleasing results. It is simple yet effective and we demonstrate its advantages both quantitatively and qualitatively. Besides, we hope our theoretical analysis can inspire future works in neural style transfer.
-
a Closed Form Solution to universal style transfer
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Hao Zhao, Anbang Yao, Yurong Chen, Li ZhangAbstract:Universal style transfer tries to explicitly minimize the losses in feature space, thus it does not require training on any pre-defined styles. It usually uses different layers of VGG network as the encoders and trains several decoders to invert the features into images. Therefore, the effect of style transfer is achieved by feature transForm. Although plenty of methods have been proposed, a theoretical analysis of feature transForm is still missing. In this paper, we first propose a novel interpretation by treating it as the optimal transport problem. Then, we demonstrate the relations of our Formulation with Former works like Adaptive Instance Normalization (AdaIN) and Whitening and Coloring TransForm (WCT). Finally, we derive a Closed-Form Solution named Optimal Style Transfer (OST) under our Formulation by additionally considering the content loss of Gatys. Comparatively, our Solution can preserve better structure and achieve visually pleasing results. It is simple yet effective and we demonstrate its advantages both quantitatively and qualitatively. Besides, we hope our theoretical analysis can inspire future works in neural style transfer. Code is available at this https URL.
Saikit Yeung - One of the best experts on this subject based on the ideXlab platform.
-
a Closed Form Solution to tensor voting theory and applications
arXiv: Computer Vision and Pattern Recognition, 2016Co-Authors: Saikit Yeung, Jiaya Jia, Chikeung Tang, Gerard MedioniAbstract:We prove a Closed-Form Solution to tensor voting (CFTV): given a point set in any dimensions, our Closed-Form Solution provides an exact, continuous and efficient algorithm for computing a structure-aware tensor that simultaneously achieves salient structure detection and outlier attenuation. Using CFTV, we prove the convergence of tensor voting on a Markov random field (MRF), thus termed as MRFTV, where the structure-aware tensor at each input site reaches a stationary state upon convergence in structure propagation. We then embed structure-aware tensor into expectation maximization (EM) for optimizing a single linear structure to achieve efficient and robust parameter estimation. Specifically, our EMTV algorithm optimizes both the tensor and fitting parameters and does not require random sampling consensus typically used in existing robust statistical techniques. We perFormed quantitative evaluation on its accuracy and robustness, showing that EMTV perForms better than the original TV and other state-of-the-art techniques in fundamental matrix estimation for multiview stereo matching. The extensions of CFTV and EMTV for extracting multiple and nonlinear structures are underway. An addendum is included in this arXiv version.
-
a Closed Form Solution to tensor voting theory and applications
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012Co-Authors: Saikit Yeung, Jiaya Jia, Chikeung Tang, Gerard MedioniAbstract:We prove a Closed-Form Solution to tensor voting (CFTV): Given a point set in any dimensions, our Closed-Form Solution provides an exact, continuous, and efficient algorithm for computing a structure-aware tensor that simultaneously achieves salient structure detection and outlier attenuation. Using CFTV, we prove the convergence of tensor voting on a Markov random field (MRF), thus termed as MRFTV, where the structure-aware tensor at each input site reaches a stationary state upon convergence in structure propagation. We then embed structure-aware tensor into expectation maximization (EM) for optimizing a single linear structure to achieve efficient and robust parameter estimation. Specifically, our EMTV algorithm optimizes both the tensor and fitting parameters and does not require random sampling consensus typically used in existing robust statistical techniques. We perFormed quantitative evaluation on its accuracy and robustness, showing that EMTV perForms better than the original TV and other state-of-the-art techniques in fundamental matrix estimation for multiview stereo matching. The extensions of CFTV and EMTV for extracting multiple and nonlinear structures are underway.