DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Je, Minkyu | - |
dc.contributor.advisor | 제민규 | - |
dc.contributor.author | Abdikarimuly, Ramazan | - |
dc.date.accessioned | 2023-06-26T19:30:50Z | - |
dc.date.available | 2023-06-26T19:30:50Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=997252&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/309424 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2022.2,[iii, 33 p. :] | - |
dc.description.abstract | We address the problem of 3D scene reconstruction from monocular video. Classical methods of scene reconstruction suffer from high computational complexity, while learning-based methods have not yet provided a general solution. In this work, we propose a novel algorithm for estimating consistent dense depth maps from learning-based depth prior with planar constraint and a full framework 3D scene reconstruction that consists of three main parts: 1) time efficient sparse visual SLAM optimization algorithm, 2) dense depth estimation and 3) weighted depth fusion. Unlike previous works, our framework provides real-time and robust performance that works in generalized, challenging and texture-poor scenes without inference-time fine-tuning. The experiments on unseen on training indoor datasets show that our framework outperforms state-of-the-art methods in terms of ”in the wild” accuracy and speed. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.title | Monocular video depth estimation with planar constraint and semantic prior for real-time 3d reconstruction | - |
dc.title.alternative | 실시간 3차원 복원을 위해 평면 제약 조건 및 의미론적 사전 정보를 활용한 단안 영상에서의 깊이 정보 추정 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 압디카림얼르 라마잔 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.