10.6.4 Multi-View Object Detection, Object Extraction

Chapter Contents (Back)
Multi-View Stereo. Object Extracton. More about the objects than basic stereo

Stenstrom, J.R., and Connolly, C.I.,
Constructing Object Models from Multiple Images,
IJCV(9), No. 3, 1992, pp. 185-212.
Springer DOI BibRef 9200
And: A2, A1:
3-D Scene Reconstruction from Multiple Intensity Images,
3DWS89(124-130). BibRef
Earlier: A2, A1:
Construction of Polyhedral Models from Multiple Range Views,
ICPR86(85-87).
See also Matching from 3-D Range Models into 2-D Intensity Scenes. BibRef

Sugimoto, A.,
Object Recognition by Combining Paraperspective Images,
IJCV(19), No. 2, August 1996, pp. 181-201.
Springer DOI 9609
BibRef

Sugimoto, A., Murota, K.,
3D Object Recognition by Combination of Perspective Images,
SPIE(1904), February 1993, pp. 183-195. BibRef 9302

Wilf, I., Manor, Y.,
Multiple-View Model-Based Inspection Of Quadric Objects,
PRL(10), 1989, pp. 33-38. BibRef 8900

Pinjo, Z., Cyganski, D., Orr, J.A.,
Determination of 3-D Object Orientation from Projections,
PRL(3), 1985, pp. 351-356. BibRef 8500

Mann, S.[Steve], Picard, R.W.[Rosalind W.],
Video Orbits of the Projective Group: A Simple Approach to Featureless Estimation of Parameters,
IP(6), No. 9, September 1997, pp. 1281-1295.
IEEE DOI 9709
BibRef

Mann, S.[Steve], Picard, R.W.[Rosalind W.],
Method and apparatus for relating and combining multiple images of the same scene or object(s),
US_Patent5,706,416, Jan 6, 1998
WWW Link. BibRef 9801
And:
Virtual Bellows: Constructing High Quality Stills from Video,
ICIP94(I: 363-367).
IEEE DOI 9411
BibRef
And: Vismod-259, 1993.
HTML Version. and
PS File. BibRef

Eisert, P., Steinbach, E.G., Girod, B.,
Automatic Reconstruction of Stationary 3-D Objects from Multiple Uncalibrated Camera Views,
CirSysVideo(10), No. 2, March 2000, pp. 261.
IEEE Top Reference. 0003
BibRef

Weng, J.Y.[Ju-Yang], Hammond, D.J.[David James],
Method and system for building three-dimensional object models,
US_Patent6,081,273, Jun 27, 2000
WWW Link. BibRef 0006

Bean, H.N.[Heather N.], Robins, M.N.[Mark N.],
Method and digital camera for indicating when image data has been captured for a three-dimensional target object,
US_Patent7,050,625, May 23, 2006
WWW Link. Multiple images to capture 3-D data. BibRef 0605

Kriegel, S.[Simon], Rink, C.[Christian], Bodenmüller, T.[Tim], Suppa, M.[Michael],
Efficient next-best-scan planning for autonomous 3D surface reconstruction of unknown objects,
RealTimeIP(10), No. 4, December 2015, pp. 611-631.
Springer DOI 1512
BibRef

Kim, S.H., Tai, Y.W., Park, J., Kweon, I.S.,
Multi-View Object Extraction With Fractional Boundaries,
IP(25), No. 8, August 2016, pp. 3639-3654.
IEEE DOI 1608
cameras BibRef

Park, J.[Jaesik], Tai, Y.W.[Yu-Wing], Cho, D., Kweon, I.S.[In So],
A Unified Approach of Multi-scale Deep and Hand-Crafted Features for Defocus Estimation,
CVPR17(2760-2769)
IEEE DOI 1711
Discrete cosine transforms, Estimation, Feature extraction, Image edge detection, Neural networks, Robustness BibRef

Park, J.[Jaesik], Oh, T.H.[Tae Hyun], Jung, J.Y.[Ji-Young], Tai, Y.W.[Yu-Wing], Kweon, I.S.[In So],
A Tensor Voting Approach for Multi-View 3D Scene Flow Estimation and Refinement,
ECCV12(IV: 288-302).
Springer DOI 1210
BibRef

Hong, R.C.[Ri-Chang], Hu, Z.Z.[Zhen-Zhen], Wang, R.X.[Ru-Xin], Wang, M.[Meng], Tao, D.C.[Da-Cheng],
Multi-View Object Retrieval via Multi-Scale Topic Models,
IP(25), No. 12, December 2016, pp. 5814-5827.
IEEE DOI 1612
feature extraction BibRef

Huang, J.J.[Jing-Jia], Yan, W.[Wei], Li, T.[Thomas], Liu, S.[Shan], Li, G.[Ge],
Learning the Global Descriptor for 3-D Object Recognition Based on Multiple Views Decomposition,
MultMed(24), 2022, pp. 188-201.
IEEE DOI 2202
Solid modeling, Object recognition, Task analysis, Shape, object recognition BibRef

Huang, J.J.[Jing-Jia], Yan, W.[Wei], Li, G.[Ge], Li, T.[Thomas], Liu, S.[Shan],
Learning Disentangled Representation for Multi-View 3D Object Recognition,
CirSysVideo(32), No. 2, February 2022, pp. 646-659.
IEEE DOI 2202
Solid modeling, Feature extraction, Task analysis, Object recognition, disentangled representation BibRef

Sun, H.Q.[Han-Qing], Cao, J.[Jiale], Pang, Y.W.[Yan-Wei],
Semantic-aware self-supervised depth estimation for stereo 3D detection,
PRL(167), 2023, pp. 164-170.
Elsevier DOI 2303
Stereo vision, 3D object detection, Self-supervised learning, Depth estimation BibRef


Zhang, J.Q.[Jin-Qing], Zhang, Y.[Yanan], Liu, Q.J.[Qing-Jie], Wang, Y.H.[Yun-Hong],
SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection,
ICCV23(3325-3334)
IEEE DOI Code:
WWW Link. 2401
BibRef

Xiong, K.X.[Kai-Xin], Gong, S.[Shi], Ye, X.Q.[Xiao-Qing], Tan, X.[Xiao], Wan, J.[Ji], Ding, E.[Errui], Wang, J.D.[Jing-Dong], Bai, X.[Xiang],
CAPE: Camera View Position Embedding for Multi-View 3D Object Detection,
CVPR23(21570-21579)
IEEE DOI 2309
BibRef

Feng, C.J.[Cheng-Jian], Jie, Z.Q.[Ze-Qun], Zhong, Y.J.[Yu-Jie], Chu, X.X.[Xiang-Xiang], Ma, L.[Lin],
AeDet: Azimuth-Invariant Multi-View 3D Object Detection,
CVPR23(21580-21588)
IEEE DOI 2309
BibRef

Xompero, A.[Alessio], Cavallaro, A.[Andrea],
Cross-camera View-overlap Recognition,
DSC22(253-269).
Springer DOI 2304
BibRef

Ho, L.N.[Long-Nhat], Tran, A.T.[Anh Tuan], Phung, Q.[Quynh], Hoai, M.[Minh],
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images,
ICCV21(12580-12590)
IEEE DOI 2203
Codes, Shape, Robustness, Task analysis, Unsupervised learning, 3D from a single image and shape-from-x, Faces BibRef

Mergy, A.[Anne], Lecuyer, G.[Gurvan], Derksen, D.[Dawa], Izzo, D.[Dario],
Vision-based Neural Scene Representations for Spacecraft,
AI4Space21(2002-2011)
IEEE DOI 2109
Pose and shape of nearby objects. Space vehicles, Surface reconstruction, Sea surface, Satellites, Shape BibRef

Goel, P.[Purvi], Cohen, L.[Loudon], Guesman, J.[James], Thamizharasan, V.[Vikas], Tompkin, J.[James], Ritchie, D.[Daniel],
Shape from Tracing: Towards Reconstructing 3D Object Geometry and SVBRDF Material from Images via Differentiable Path Tracing,
3DV20(1186-1195)
IEEE DOI 2102
Image reconstruction, Geometry, Lighting, Optimization, Surface reconstruction, Rendering (computer graphics), Shape, Mesh models BibRef

He, X.W.[Xin-Wei], Huang, T.T.[Teng-Teng], Bai, S.[Song], Bai, X.[Xiang],
View N-Gram Network for 3D Object Retrieval,
ICCV19(7514-7523)
IEEE DOI 2004
image representation, image retrieval, image sequences, learning (artificial intelligence), Computational modeling BibRef

Birdal, T.[Tolga], Simsekli, U.[Umut],
Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope,
CVPR19(11097-11108).
IEEE DOI 2002
synchronization of correspondences across multiple sets of objects. BibRef

Abdul, H.M.[Haseeb Muhammad], Danijela, R.D.[Ristic-Durrant], Axel, G.[Gräser], Milan, B.[Banic], Dušan, S.[Stamenkovic],
Multi-disnet: Machine Learning-based Object Distance Estimation from Multiple Cameras,
CVS19(457-469).
Springer DOI 1912
BibRef

Mélou, J.[Jean], Quéau, Y.[Yvain], Castan, F.[Fabien], Durou, J.D.[Jean-Denis],
A Splitting-Based Algorithm for Multi-view Stereopsis of Textureless Objects,
SSVM19(51-63).
Springer DOI 1909
BibRef

Ulusoy, A.O., Black, M.J., Geiger, A.,
Semantic Multi-view Stereo: Jointly Estimating Objects and Voxels,
CVPR17(4531-4540)
IEEE DOI 1711
Cameras, Image reconstruction, Probabilistic logic, Semantics, Shape, Solid modeling, BibRef

Manfredi, G.[Guido], Devy, M.[Michel], Sidobre, D.[Daniel],
Textured Object Recognition: Balancing Model Robustness and Complexity,
CAIP15(I:52-63).
Springer DOI 1511
ASIFT descriptor. Use robust descriptors and a small number of views for best results. BibRef

Sølund, T.[Thomas], Savarimuthu, T.R.[Thiusius Rajeeth], Buch, A.G.[Anders Glent], Beck, A.B.[Anders Billesø], Krüger, N.[Norbert], Aanæs, H.[Henrik],
Teach it Yourself: Fast Modeling of Industrial Objects for 6D Pose Estimation,
CVS15(289-302).
Springer DOI 1507
Generate 3D model by placing the object in 2 different positions. BibRef

Faulhammer, T.[Thomas], Zillich, M.[Michael], Vincze, M.[Markus],
Multi-view hypotheses transfer for enhanced object recognition in clutter,
MVA15(10-13)
IEEE DOI 1507
Cameras BibRef

Modi, R.A.[Ravindra A.], Goyal, S.R.[Satish Raj],
An efficient algorithm for 3-D object reconstruction from 2-D images,
ICIIP11(1-4).
IEEE DOI 1112
Visual hull from multiple imges, then refine using stereo. BibRef

Jazayeri, I., Fraser, C.S.[Clive S.], Cronk, S.[Simon],
Automated 3D Object Reconstruction Via Multi-Image Close-Range Photogrammetry,
CloseRange10(xx-yy).
PDF File. 1006
BibRef

Jazayeri, I., Fraser, C.S.,
Interest Operators in Close-Range Object Reconstruction,
ISPRS08(B5: 69 ff).
PDF File. 0807
BibRef

Deschenes, J.D., Lambert, P., Perreault, S., Martel-Brisson, N., Zoso, N., Zaccarin, A., Hebert, P., Bouchard, S., Gosselin, C.M.,
A Cable-driven Parallel Mechanism for Capturing Object Appearance from Multiple Viewpoints,
3DIM07(367-374).
IEEE DOI 0708
A means to move a camera around the object in predefined ways to get the description. BibRef

Lanman, D.[Douglas], Crispell, D.[Daniel], Taubin, G.[Gabriel],
Surround Structured Lighting for Full Object Scanning,
3DIM07(107-116).
IEEE DOI 0708
BibRef

Crispell, D.[Daniel], Lanman, D.[Douglas], Sibley, P.G.[Peter G.], Zhao, Y.[Yong], Taubin, G.[Gabriel],
Beyond Silhouettes: Surface Reconstruction Using Multi-Flash Photography,
3DPVT06(405-412).
IEEE DOI 0606
BibRef

Sato, T.[Taichi], Saito, H.[Hideo], Ozawa, S.[Shinji],
3d Shape Recovery of Non-convex Object from Rotation,
ICPR00(Vol I: 742-745).
IEEE DOI 0009
BibRef

Okutomi, M.[Masatoshi], Sugimoto, S.[Shigeki],
Shape Recovery of Rotating Object Using Weighted Voting of Spatio-temporal Images,
ICPR00(Vol I: 790-793).
IEEE DOI 0009
BibRef

de Jong, J.J., Buurman, J.,
Learning 3D Object Descriptions from a Set of Stereo Vision Observations,
ICPR92(I:768-771).
IEEE DOI BibRef 9200

Kim, H.S., Jain, R.C., and Volz, R.A.,
Object Recognition Using Multiple Views,
CRA85(28-33). BibRef 8500

Chapter on Stereo: Three Dimensional Descriptions from Two or More Views, Binocular, Trinocular continues in
Large Scale Multi-View Stereo, Internet Scale, Many Views .


Last update:Nov 26, 2024 at 16:40:19