[논문]Deep Depth from Uncalibrated Small Motion Clip

Im, Sunghoon; Ha, Hyowon; Jeon, Hae-Gon; Lin, Stephen; Kweon, In So

doi:10.1109/tpami.2019.2946806

[해외논문] Deep Depth from Uncalibrated Small Motion Clip

IEEE transactions on pattern analysis and machine intelligence, v.43 no.4, 2021년, pp.1225 - 1238

Im, Sunghoon (Daegu Gyeongbuk Institute of Science and Technology, Department of Information and Communication Engineering, Daegu, Republic of Korea) , Ha, Hyowon (Apple Inc., Cupertino, CA, USA) , Jeon, Hae-Gon (Gwangju Institute of Science and Technology, Artificial Intelligence Graduate School and the School of Electrical Engineering and Computer Science, Gwangju, Republic of Korea) , Lin, Stephen (Microsoft Research, Beijing, China) , Kweon, In So (Korea Advanced Institute of Science and Technology, School of Electrical Engineering, Daejeon, Republic of Korea)

Abstract ▼ AI-Helper

We propose a novel approach to infer a high-quality depth map from a set of images with small viewpoint variations. In general, techniques for depth estimation from small motion consist of camera pose estimation and dense reconstruction. In contrast to prior approaches that recover scene geometry and camera motions using pre-calibrated cameras, we introduce in this paper a self-calibrating bundle adjustment method tailored for small motion which enables computation of camera poses without the need for camera calibration. For dense depth reconstruction, we present a convolutional neural network called DPSNet (Deep Plane Sweep Network) whose design is inspired by best practices of traditional geometry-based approaches. Rather than directly estimating depth or optical flow correspondence from image pairs as done in many previous deep learning methods, DPSNet takes a plane sweep approach that involves building a cost volume from deep features using the plane sweep algorithm, regularizing the cost volume, and regressing the depth map from the cost volume. The cost volume is constructed using a differentiable warping process that allows for end-to-end training of the network. Through the effective incorporation of conventional multiview stereo concepts within a deep learning framework, the proposed method achieves state-of-the-art results on a variety of challenging datasets.

참고문헌 (57)

10.1109/ICCV.2017.17
10.1109/CVPR.2017.660
10.1109/ICPR.2002.1048370
MA, LILI, CHEN, YANGQUAN, MOORE, KEVIN L.. RATIONAL RADIAL DISTORTION MODELS OF CAMERA LENSES WITH ANALYTICAL SOLUTION FOR DISTORTION CORRECTION. International journal of information acquisition : iA, vol.1, no.2, 135-147.

상세보기
Snavely, Noah, Seitz, Steven M., Szeliski, Richard. Modeling the World from Internet Photo Collections. International journal of computer vision, vol.80, no.2, 189-210.

상세보기
Fang, J.-Q, Huang, T.S. Solving three-dimensional small-rotation motion equations: Uniqueness, algorithms, and numerical results. Computer vision, graphics, and image processing, vol.26, no.2, 183-206.

상세보기
Proc Eur Conf Comput Vis Spatial pyramid pooling in deep convolutional networks for visual recognition he 2014 346
Proc 7th Int Joint Conf Artif Intell An iterative image registration technique with an application to stereo vision lucas 1981 81 674
10.5244/C.2.23
10.1214/aoms/1177703732
10.1109/ICCV.2017.253
10.1109/ICRA.2018.8461251
10.1007/978-3-030-01237-3_47
10.1007/978-3-319-46487-9_10
10.1109/ICCV.2015.102
10.1109/CVPR.1996.517097
10.1109/CVPR.1998.698610
Adv Neural Inf Process Syst Efficient inference in fully connected CRFs with gaussian edge potentials krähenbühl 2011 109
Oliensis, John. The Least-Squares Error for Structure from Infinitesimal Motion. International journal of computer vision, vol.61, no.3, 1-41.

상세보기
Oliensis, John. "A Multi-Frame Structure-from-Motion Algorithm under Perspective Projection." International journal of computer vision, v.34 no.2/3 (1999), pp. 163-192, doi:10.1023/A:1008139920864.
10.1109/CVPR.2017.596
Civera, J., Davison, A.J., Montiel, J.. Inverse Depth Parametrization for Monocular SLAM. IEEE transactions on robotics : a publication of the IEEE Robotics and Automation Society, vol.24, no.5, 932-945.

상세보기
IEEE Trans Pattern Anal Mach Intell A quantitative evaluation of confidence measures for stereo vision hu 2012 10.1109/TPAMI.2012.46 34 2121

상세보기
10.1109/ICCV.2015.316
Proc Annu Conf Neural Inf Process Syst Learning a multi-view stereo machine kar 2017 364
10.1109/CVPR.2019.00567
10.1007/978-3-319-46487-9_31
10.1109/CVPR.2013.47
Proc Int Conf Learn Representations BA-net: Dense bundle adjustment networks tang 2019 1
10.1109/CVPR.2018.00567
Proc Int Conf Learn Representations DPSNet: End-to-end deep plane sweep stereo im 2019 1
Multiple View Geometry in Computer Vision hartley 2003
He, Kaiming, Sun, Jian, Tang, Xiaoou. Guided Image Filtering. IEEE transactions on pattern analysis and machine intelligence, vol.35, no.6, 1397-1409.

상세보기
10.1145/1179352.1141964
Triggs, B., McLauchlan, P. F., Hartley, R. I., Fitzgibbon, A. W.. Bundle Adjustment - A Modern Synthesis. Lecture notes in computer science, vol.1883, 298-372.

상세보기
10.1109/CVPR.2011.5995626
Proc Int Conf Comput Vis Multiple view geometry and the l-norm kahl 2005 1002
Proc IEEE Conf Comput Vis Pattern Recognit Recovering camera motion using Linfty minimization sim 2006 1230
Kahl, Fredrik, Agarwal, Sameer, Chandraker, Manmohan Krishna, Kriegman, David, Belongie, Serge. Practical Global Optimization for Multiview Geometry. International journal of computer vision, vol.79, no.3, 271-284.

상세보기
Okutomi, M., Kanade, T.. A multiple-baseline stereo. IEEE transactions on pattern analysis and machine intelligence, vol.15, no.4, 353-363.

상세보기
10.1109/CVPR.2008.4587671
Proc IEEE Conf Comput Vis Pattern Recognit DeepStereo: Learning to predict new views from the worlds imagery flynn 2016 5515
10.1109/CVPR.2018.00298
10.1109/CVPR.2011.5995372
Proc Annu Conf Neural Inf Process Syst Spatial transformer networks jaderberg 2015 2017
10.1109/CVPR.2014.509
Micro-baseline stereo joshi 2014
10.1109/3DV.2017.00081
10.1109/CVPR.2016.584
Ceres solver agarwal 0
10.1109/IROS.2012.6385773
10.1109/CVPR.2016.445
Zhang, Z.. A flexible new technique for camera calibration. IEEE transactions on pattern analysis and machine intelligence, vol.22, no.11, 1330-1334.

상세보기
Proc Int Conf Learn Representations Multi-scale context aggregation by dilated convolutions yu 2016 1
Chen, Liang-Chieh, Papandreou, George, Kokkinos, Iasonas, Murphy, Kevin, Yuille, Alan L.. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE transactions on pattern analysis and machine intelligence, vol.40, no.4, 834-848.

상세보기
10.1109/ICCV.2013.458
Blender 0

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

원문 URL 링크

DOI : 10.1109/TPAMI.2019.2946806
IEEE Computer Society : 저널 > 논문
IEEE : 저널 > 논문

*원문 PDF 파일 및 링크정보가 존재하지 않을 경우 KISTI DDS 시스템에서 제공하는 원문복사서비스를 사용할 수 있습니다.

저작권 관리 안내

내보내기 메뉴

내보내기 구분

파일저장
인쇄
메일전송

구성항목

기본정보
상세정보

관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관

저장형식

Text(ASCII format)
Excel format
RefWorks Direct Export
RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley

메일정보

받는사람 (필수): @
보내는사람 (선택): @
제목
내용: KISTI 검색결과 이메일 서비스

안내

총 건의 자료가 검색되었습니다.

다운받으실 자료의 인덱스를 입력하세요. (1-10,000)

검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다.

데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요)

다운로드 파일은 UTF-8 형태로 저장됩니다.
파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오.

Text(ASCII format)
Excel format

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

AI-Helper ※ AI-Helper는 을 사용합니다.

AI-Helper

안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

연합인증