國立高雄大學圖資館 |

登入

回首頁

Robust Synchronization and Its Applications in 3D Computer Vision.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Robust Synchronization and Its Applications in 3D Computer Vision.
作者:	Shi, Yunpeng.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, 2020
面頁冊數:	216 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-05, Section: B.
附註:	Advisor: Lerman, Gilad.
Contained By:	Dissertations Abstracts International82-05B.
標題:	Applied mathematics.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28093483
ISBN:	9798678181664

Robust Synchronization and Its Applications in 3D Computer Vision.
Shi, Yunpeng.

Robust Synchronization and Its Applications in 3D Computer Vision. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 216 p.

Source: Dissertations Abstracts International, Volume: 82-05, Section: B.

Thesis (Ph.D.)--University of Minnesota, 2020.

This item must not be sold to any third party vendors.

This dissertation includes five works of my Ph.D. research. It starts with an introduction to 3D reconstruction and its associated synchronization problems, followed by the robust synchronization algorithms and their theoretical guarantees.Common 3D reconstruction tasks rely on accurate estimation of camera rotations and locations. These estimation problems are often solved by using graph optimization methods and can be mathematically formulated as synchronization problems. The synchronization problems ask to find the absolute states (e.g. rotations, locations) of graph nodes from the given noisy and corrupted relative states among pairs of nodes. The most common synchronization problem is group synchronization, where the states of nodes are elements of certain mathematical group. It asks to find the underlying group elements (e.g. absolute rotations) for each node from the given noisy and corrupted group ratios (e.g. relative rotations) among pairs of nodes.In order to solve this problem, we first propose cycle-edge message passing (CEMP) framework that estimates the corruption levels of group ratios for any compact group. We establish the exact recovery and linear convergence guarantees with adversarial corruption and its stability to sub-Gaussian noise. We further show that under a uniform corruption model, the recovery results are sharp in terms of an information-theoretic bound.We next extend the idea of CEMP and develop message passing least squares (MPLS) framework for directly solving group elements under both high corruption and noise. We carefully refine the framework for specific applications of rotation and permutation synchronization in 3D computer vision. Both applications demonstrate the superior performance of MPLS over the state-of-the-art methods.Finally, we discuss camera location estimation problem which can be viewed as a variant of group synchronization problem on the noncompact group R.

ISBN: 9798678181664Subjects--Topical Terms:

377601
Applied mathematics.
Subjects--Index Terms:

Message passing

Robust Synchronization and Its Applications in 3D Computer Vision.
LDR:03471nmm a2200373 4500 001 616380
005 20220513114321.5
008 220920s2020 ||||||||||||||||| ||eng d
020 $a 9798678181664
035 $a (MiAaPQ)AAI28093483
035 $a AAI28093483
040 $a MiAaPQ $c MiAaPQ
100 1 $a Shi, Yunpeng. $3 915539
245 1 0 $a Robust Synchronization and Its Applications in 3D Computer Vision.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 216 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-05, Section: B.
500 $a Advisor: Lerman, Gilad.
502 $a Thesis (Ph.D.)--University of Minnesota, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a This dissertation includes five works of my Ph.D. research. It starts with an introduction to 3D reconstruction and its associated synchronization problems, followed by the robust synchronization algorithms and their theoretical guarantees.Common 3D reconstruction tasks rely on accurate estimation of camera rotations and locations. These estimation problems are often solved by using graph optimization methods and can be mathematically formulated as synchronization problems. The synchronization problems ask to find the absolute states (e.g. rotations, locations) of graph nodes from the given noisy and corrupted relative states among pairs of nodes. The most common synchronization problem is group synchronization, where the states of nodes are elements of certain mathematical group. It asks to find the underlying group elements (e.g. absolute rotations) for each node from the given noisy and corrupted group ratios (e.g. relative rotations) among pairs of nodes.In order to solve this problem, we first propose cycle-edge message passing (CEMP) framework that estimates the corruption levels of group ratios for any compact group. We establish the exact recovery and linear convergence guarantees with adversarial corruption and its stability to sub-Gaussian noise. We further show that under a uniform corruption model, the recovery results are sharp in terms of an information-theoretic bound.We next extend the idea of CEMP and develop message passing least squares (MPLS) framework for directly solving group elements under both high corruption and noise. We carefully refine the framework for specific applications of rotation and permutation synchronization in 3D computer vision. Both applications demonstrate the superior performance of MPLS over the state-of-the-art methods.Finally, we discuss camera location estimation problem which can be viewed as a variant of group synchronization problem on the noncompact group R.
520 $a 3. We present and prove an exact recovery theory for the state-of-the-art least unsquared deviations (LUD) solver under adversarial corruption. We then develop the all-about-that-base (AAB) preprocessing step for detecting corrupted edges. We demonstrate that the application of AAB significantly improves the performance of common camera location solvers on both synthetic and real data.
590 $a School code: 0130.
650 4 $a Applied mathematics. $3 377601
650 4 $a Computer science. $3 199325
650 4 $a Statistics. $3 182057
653 $a Message passing
653 $a Robust estimation
653 $a Structure from motion
653 $a Synchronization
690 $a 0364
690 $a 0984
690 $a 0463
710 2 $a University of Minnesota. $b Mathematics. $3 603145
773 0 $t Dissertations Abstracts International $g 82-05B.
790 $a 0130
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28093483