18.6.2 Motion, Shape from Motion for RGB-D Sensors, Kinect Motion

Chapter Contents (Back)
RGB-D. Motion and Depth.

Yang, J.Y.[Jing-Yu], Ye, X.C.[Xin-Chen], Li, K.[Kun], Hou, C.P.[Chun-Ping], Wang, Y.[Yao],
Color-Guided Depth Recovery From RGB-D Data Using an Adaptive Autoregressive Model,
IP(23), No. 8, August 2014, pp. 3443-3458.
IEEE DOI 1408
BibRef
Earlier: A1, A2, A3, A4, Only:
Depth Recovery Using an Adaptive Color-Guided Auto-Regressive Model,
ECCV12(V: 158-171).
Springer DOI 1210
autoregressive processes. from low quality ToF cameras BibRef

Li, K.[Kun], Zhu, Y.M.[Yan-Ming], Yang, J.Y.[Jing-Yu], Jiang, J.M.[Jian-Min],
Video super-resolution using an adaptive superpixel-guided auto-regressive model,
PR(51), No. 1, 2016, pp. 59-71.
Elsevier DOI 1601
Video super-resolution BibRef

Hadfield, S.[Simon], Bowden, R.[Richard],
Scene Particles: Unregularized Particle-Based Scene Flow Estimation,
PAMI(36), No. 3, March 2014, pp. 564-576.
IEEE DOI 1403
BibRef
And:
Scene Flow Estimation using Intelligent Cost Functions,
BMVC14(xx-yy).
HTML Version. 1410
BibRef
Earlier:
Go with the Flow: Hand Trajectories in 3D via Clustered Scene Flow,
ICIAR12(I: 285-295).
Springer DOI 1206
BibRef
Earlier:
Kinecting the dots: Particle based scene flow from depth sensors,
ICCV11(2290-2295).
IEEE DOI 1201
image sequences. 3D flow, not just 2-D optic flow. With Kinect sensor. BibRef

Lebeda, K.[Karel], Hadfield, S.[Simon], Bowden, R.[Richard],
Direct-from-Video: Unsupervised NRSfM,
6DPose16(III: 578-594).
Springer DOI 1611
BibRef
And:
Dense Rigid Reconstruction from Unstructured Discontinuous Video,
3DRR15(814-822)
IEEE DOI 1602
BibRef
Earlier:
2D or Not 2D: Bridging the Gap Between Tracking and Structure from Motion,
ACCV14(IV: 642-658).
Springer DOI 1504
BibRef

Wang, K., Zhang, G.F.[Guo-Feng], Bao, H.J.[Hu-Jun],
Robust 3D Reconstruction With an RGB-D Camera,
IP(23), No. 11, November 2014, pp. 4893-4906.
IEEE DOI 1410
Cameras BibRef

Zhang, G.F.[Guo-Feng], Jia, J.Y.[Jia-Ya], Bao, H.J.[Hu-Jun],
Simultaneous multi-body stereo and segmentation,
ICCV11(826-833).
IEEE DOI 1201
Multi-view stereo. Dense depth map. Segmentation from monocular image sequence. BibRef


Bai, J., Yang, J., Ye, X., Hou, C.,
Depth refinement for binocular kinect RGB-D cameras,
VCIP16(1-4)
IEEE DOI 1701
Cameras BibRef

Cheng, S.C.[Shyi-Chyi], Su, J.Y.[Jui-Yuan], Chen, J.M.[Jing-Min], Hsieh, J.W.[Jun-Wei],
Model-Based 3D Scene Reconstruction Using a Moving RGB-D Camera,
MMMod17(I: 214-225).
Springer DOI 1701
BibRef

Kam, H.C.[Ho Chuen], Wong, K.H.[Kin Hong], Zhang, B.[Baiwu],
Dual Back-to-Back Kinects for 3-D Reconstruction,
ISVC16(I: 858-867).
Springer DOI 1701
rgb-d BibRef

Kehl, W.[Wadim], Navab, N.[Nassir], Ilic, S.[Slobodan],
Coloured signed distance fields for full 3D object reconstruction,
BMVC14(xx-yy).
HTML Version. 1410
geometry of an object using an RGB-D device. depth and color and motion. BibRef

Xiao, J.X.[Jian-Xiong], Owens, A.[Andrew], Torralba, A.[Antonio],
SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels,
ICCV13(1625-1632)
IEEE DOI 1403
Dataset, Scene Understanding.
WWW Link. RGB-D Video dataset. Camera pose and object labels. Interactive reconstruction process. BibRef

da Silva Pires, D.[David], Cesar, Jr., R.M.[Roberto M.], Velho, L.[Luiz],
Motion Estimation from RGB-D Images Using Graph Homomorphism,
CIARP13(II:487-494).
Springer DOI 1311
BibRef

Chapter on Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion continues in
Spatio-Temporal Analysis -- Many Frames .


Last update:Sep 18, 2017 at 11:34:11