19.9.1 Shape from Motion, Learning, Neural Nets

Chapter Contents (Back)
Motion, Structure. Shape from Motion.

Zheng, E., Ji, D.H.[Ding-Huang], Dunn, E.[Enrique], Frahm, J.M.[Jan-Michael],
Self-Expressive Dictionary Learning for Dynamic 3D Reconstruction,
PAMI(40), No. 9, September 2018, pp. 2223-2237.
IEEE DOI 1808
BibRef
Earlier:
Sparse Dynamic 3D Reconstruction from Unsynchronized Videos,
ICCV15(4435-4443)
IEEE DOI 1602
BibRef
Earlier: A2, A3, A4, Only:
3D Reconstruction of Dynamic Textures in Crowd Sourced Data,
ECCV14(I: 143-158).
Springer DOI 1408
Trajectory, Image reconstruction, Cameras, Sequential analysis, Dynamics, Streaming media, dynamic 3D reconstruction BibRef

Ji, D.H.[Ding-Huang], Dunn, E.[Enrique], Frahm, J.M.[Jan-Michael],
Spatio-Temporally Consistent Correspondence for Dense Dynamic Scene Modeling,
ECCV16(VI: 3-18).
Springer DOI 1611
BibRef

Schonberger, J.L.[Johannes L.], Frahm, J.M.[Jan-Michael],
Structure-from-Motion Revisited,
CVPR16(4104-4113)
IEEE DOI 1612
BibRef

Schonberger, J.L.[Johannes L.], Radenovic, F.[Filip], Chum, O.[Ondrej], Frahm, J.M.[Jan-Michael],
From single image query to detailed 3D reconstruction,
CVPR15(5126-5134)
IEEE DOI 1510
BibRef

Schonberger, J.L.[Johannes L.], Berg, A.C.[Alexander C.], Frahm, J.M.[Jan-Michael],
Efficient Two-View Geometry Classification,
GCPR15(53-64).
Springer DOI 1511
Award, GCPR, HM. BibRef
And:
PAIGE: PAirwise Image Geometry Encoding for improved efficiency in Structure-from-Motion,
CVPR15(1009-1018)
IEEE DOI 1510
BibRef

Heinly, J.[Jared], Schonberger, J.L.[Johannes L.], Dunn, E.[Enrique], Frahm, J.M.[Jan-Michael],
Reconstructing the world* in six days,
CVPR15(3287-3295)
IEEE DOI 1510
Large scale for millions of images. BibRef

Heinly, J.[Jared], Dunn, E.[Enrique], Frahm, J.M.[Jan-Michael],
Recovering Correct Reconstructions from Indistinguishable Geometry,
3DV14(377-384)
IEEE DOI 1503
BibRef
And:
Correcting for Duplicate Scene Structure in Sparse 3D Reconstruction,
ECCV14(IV: 780-795).
Springer DOI 1408
Cameras. repeating structures. BibRef

Mandal, M., Dhar, V., Mishra, A., Vipparthi, S.K.,
3DFR: A Swift 3D Feature Reductionist Framework for Scene Independent Change Detection,
SPLetters(26), No. 12, December 2019, pp. 1882-1886.
IEEE DOI 2001
feature extraction, image motion analysis, image sequences, learning (artificial intelligence), neural nets, reductionist BibRef

Zhou, H.Z.[Hui-Zhong], Ummenhofer, B.[Benjamin], Brox, T.[Thomas],
DeepTAM: Deep Tracking and Mapping with Convolutional Neural Networks,
IJCV(128), No. 3, March 2020, pp. 756-769.
Springer DOI 2003
Code, Tracking.
WWW Link. BibRef

Mohamed, H.[Hassan], Nadaoka, K.[Kazuo], Nakamura, T.[Takashi],
Towards Benthic Habitat 3D Mapping Using Machine Learning Algorithms and Structures from Motion Photogrammetry,
RS(12), No. 1, 2020, pp. xx-yy.
DOI Link 2001
BibRef

Gu, S.H.[Shu-Hang], Guo, S.[Shi], Zuo, W.M.[Wang-Meng], Chen, Y.J.[Yun-Jin], Timofte, R.[Radu], Van Gool, L.J.[Luc J.], Zhang, L.[Lei],
Learned Dynamic Guidance for Depth Image Reconstruction,
PAMI(42), No. 10, October 2020, pp. 2437-2452.
IEEE DOI 2009
Task analysis, Analytical models, Optimization, Image reconstruction, Training data, Data models, Network architecture BibRef

Jin, F.S.[Fu-Sheng], Zhao, Y.[Yu], Wan, C.B.[Chuan-Bing], Yuan, Y.[Ye], Wang, S.[Shuliang],
Unsupervised Learning of Depth from Monocular Videos Using 3D-2D Corresponding Constraints,
RS(13), No. 9, 2021, pp. xx-yy.
DOI Link 2105
BibRef

Liu, M.Y.[Meng-Yi], Wang, S.H.[Shu-Hui], Guo, Y.L.[Yu-Lan], He, Y.[Yuan], Xue, H.[Hui],
Pano-SfMLearner: Self-Supervised Multi-Task Learning of Depth and Semantics in Panoramic Videos,
SPLetters(28), 2021, pp. 832-836.
IEEE DOI 2105
BibRef

Li, Z.Q.[Zheng-Qi], Dekel, T.[Tali], Cole, F.[Forrester], Tucker, R.[Richard], Snavely, N.[Noah], Liu, C.[Ce], Freeman, W.T.[William T.],
MannequinChallenge: Learning the Depths of Moving People by Watching Frozen People,
PAMI(43), No. 12, December 2021, pp. 4229-4241.
IEEE DOI 2112
BibRef
Earlier:
Learning the Depths of Moving People by Watching Frozen People,
CVPR19(4516-4525).
IEEE DOI 2002
Award, CVPR, HM. Cameras, Visualization, Internet, Image reconstruction, Natural languages, Training data, Navigation, dynamic scene reconstruction BibRef

Nunes, U.M.[Urbano Miguel], Demiris, Y.F.[Yi-Fannis],
Robust Event-Based Vision Model Estimation by Dispersion Minimisation,
PAMI(44), No. 12, December 2022, pp. 9561-9573.
IEEE DOI 2212
BibRef
Earlier:
Entropy Minimisation Framework for Event-based Vision Model Estimation,
ECCV20(V:161-176).
Springer DOI 2011
BibRef
And:
Online Unsupervised Learning of the 3D Kinematic Structure of Arbitrary Rigid Bodies,
ICCV19(3808-3816)
IEEE DOI 2004
Dispersion, Estimation, Cameras, Optical imaging, Optimization, Computational modeling, Motion estimation, Event-based vision, real-time motion estimation. feature extraction, image colour analysis, image motion analysis, unsupervised learning, online unsupervised learning, Tracking BibRef

Wang, Y.M.[Ya-Ming], Peng, X.Y.[Xiang-Yang], Huang, W.Q.[Wen-Qing], Ye, X.P.[Xiao-Ping], Jiang, M.F.[Ming-Feng],
Self-supervised non-rigid structure from motion with improved training of Wasserstein GANs,
IET-CV(17), No. 4, 2023, pp. 404-414.
DOI Link 2306
neural nets BibRef


Hui, T.W.[Tak-Wai],
RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes,
CVPR22(1665-1674)
IEEE DOI 2210
Adaptation models, Dynamics, Modulation, Estimation, Training data, Cameras, 3D from single images, Robot vision BibRef

Xie, Y.M.[Yi-Ming], Gadelha, M.[Matheus], Yang, F.T.[Feng-Ting], Zhou, X.W.[Xiao-Wei], Jiang, H.[Huaizu],
PlanarRecon: Realtime 3D Plane Detection and Reconstruction from Posed Monocular Videos,
CVPR22(6209-6218)
IEEE DOI 2210
Geometry, Image analysis, Fuses, Neural networks, Streaming media, Real-time systems, 3D from multi-view and sensors, Scene analysis and understanding BibRef

Gomes, P.[Pedro], Rossi, S.[Silvia], Toni, L.[Laura],
Spatio-Temporal Graph-RNN for Point Cloud Prediction,
ICIP21(3428-3432)
IEEE DOI 2201
Geometry, Correlation, Network topology, Simulation, Dynamics, Transform coding, Point Cloud, Point-based models BibRef

Li, S.Y.[Si-Yuan], Luo, Y.[Yue], Zhu, Y.[Ye], Zhao, X.[Xun], Li, Y.[Yu], Shan, Y.[Ying],
Enforcing Temporal Consistency in Video Depth Estimation,
PBDL21(1145-1154)
IEEE DOI 2112
Measurement, Estimation, Benchmark testing, Stability analysis, Computational efficiency BibRef

Graham, B., Novotny, D.,
RidgeSfM: Structure from Motion via Robust Pairwise Matching Under Depth Uncertainty,
3DV20(652-662)
IEEE DOI 2102
Cameras, Pipelines, Image reconstruction, Bundle adjustment, Deep learning, Standards, Task analysis, RidgeSfM, monocular depth prediction BibRef

Liu, H., Hua, G., Huang, W.,
Motion Rectification Network for Unsupervised Learning of Monocular Depth and Camera Motion,
ICIP20(2805-2809)
IEEE DOI 2011
Cameras, Dynamics, Pipelines, Unsupervised learning, Motion estimation. BibRef

Moreau, A., Mancas, M., Dutoit, T.,
Unsupervised depth prediction from monocular sequences: Improving performances through instance segmentation,
CRV20(54-61)
IEEE DOI 2006
Monocular depth estimation, Instance segmentation, Multi-task learning BibRef

Wu, Z., Wu, X., Zhang, X., Wang, S., Ju, L.,
Spatial Correspondence With Generative Adversarial Network: Learning Depth From Monocular Videos,
ICCV19(7493-7503)
IEEE DOI 2004
cameras, image matching, image motion analysis, image sequences, learning (artificial intelligence), mobile robots, Chebyshev approximation BibRef

Gordon, A., Li, H., Jonschkowski, R., Angelova, A.,
Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown Cameras,
ICCV19(8976-8985)
IEEE DOI 2004
cameras, image motion analysis, multimedia Web sites, object detection, social networking (online), BibRef

Zhou, J., Wang, Y., Qin, K., Zeng, W.,
Unsupervised High-Resolution Depth Learning From Videos With Dual Networks,
ICCV19(6871-6880)
IEEE DOI 2004
image resolution, image sampling, image texture, neural nets, stereo image processing, unsupervised learning, Network architecture BibRef

Zhang, H.K.[Hao-Kui], Li, Y.[Ying], Cao, Y.Z.H.[Yuan-Zhou-Han], Liu, Y.[Yu], Shen, C.H.[Chun-Hua], Yan, Y.L.[You-Liang],
Exploiting Temporal Consistency for Real-Time Video Depth Estimation,
ICCV19(1725-1734)
IEEE DOI 2004
Code, Depth from Motion.
WWW Link. convolutional neural nets, learning (artificial intelligence), video signal processing, Streaming media BibRef

Liu, C.[Chao], Gu, J.[Jinwei], Kim, K.[Kihwan], Narasimhan, S.G.[Srinivasa G.], Kautz, J.[Jan],
Neural RGB(r)D Sensing: Depth and Uncertainty From a Video Camera,
CVPR19(10978-10987).
IEEE DOI 2002
BibRef

Perrone, J.A.[John A.], Cree, M.J.[Michael J.], Hedayati, M.[Mohammad],
Using the Properties of Primate Motion Sensitive Neurons to Extract Camera Motion and Depth from Brief 2-D Monocular Image Sequences,
CAIP19(I:600-612).
Springer DOI 1909
BibRef

Gwn, K., Reddy, K., Giering, M., Bernal, E.A.,
Generative Adversarial Networks for Depth Map Estimation from RGB Video,
PBVS18(1258-12588)
IEEE DOI 1812
Cameras, Estimation, Sensors, Optical imaging, Laser radar, Training BibRef

Wang, F.E.[Fu-En], Hu, H.N.[Hou-Ning], Cheng, H.T.[Hsien-Tzu], Lin, J.T.[Juan-Ting], Yang, S.T.[Shang-Ta], Shih, M.L.[Meng-Li], Chu, H.K.[Hung-Kuo], Sun, M.[Min],
Self-supervised Learning of Depth and Camera Motion from 360° Videos,
ACCV18(V:53-68).
Springer DOI 1906
BibRef

Pinard, C.[Clément], Chevalley, L.[Laure], Manzanera, A.[Antoine], Filliat, D.[David],
Learning Structure-from-Motion from Motion,
DeepLearn-G18(III:363-376).
Springer DOI 1905
BibRef

Klodt, M.[Maria], Vedaldi, A.[Andrea],
Supervising the New with the Old: Learning SFM from SFM,
ECCV18(X: 713-728).
Springer DOI 1810
BibRef

Ummenhofer, B.[Benjamin], Zhou, H.Z.[Hui-Zhong], Uhrig, J., Mayer, N., Ilg, E., Dosovitskiy, A., Brox, T.[Thomas],
DeMoN: Depth and Motion Network for Learning Monocular Stereo,
CVPR17(5622-5631)
IEEE DOI 1711
Adaptive optics, Cameras, Computer architecture, Estimation, Optical fiber networks, Optical imaging, Training BibRef

Schöning, J.[Julius], Behrens, T.[Thea], Faion, P.[Patrick], Kheiri, P.[Peyman], Heidemann, G.[Gunther], Krumnack, U.[Ulf],
Structure from Motion by Artificial Neural Networks,
SCIA17(I: 146-158).
Springer DOI 1706
BibRef

Schöning, J.[Julius], Heidemann, G.[Gunther],
Bio-Inspired Architecture for Deriving 3D Models from Video Sequences,
3DModelApp16(II: 62-76).
Springer DOI 1704
BibRef

Kumar, A.C.S.[Arun C. S.], Bódis-Szomorú, A.[András], Bhandarkar, S.[Suchendra], Prasad, M.[Mukta],
Class-Specific Object Pose Estimation and Reconstruction Using 3D Part Geometry,
DeepLearn16(III: 280-295).
Springer DOI 1611
BibRef

Scheer, J.[Jonas], Fritz, M.[Mario], Grau, O.[Oliver],
Learning to Select Long-Track Features for Structure-From-Motion and Visual SLAM,
GCPR16(402-413).
Springer DOI 1611
BibRef

Banterle, F.[Francesco], Gong, R.[Rui], Corsini, M.[Massimiliano], Ganovelli, F.[Fabio], Van Gool, L.J.[Luc J.], Cignoni, P.[Paolo],
A Deep Learning Method for Frame Selection in Videos for Structure from Motion Pipelines,
ICIP21(3667-3671)
IEEE DOI 2201
Time-frequency analysis, Structure from motion, Video sequences, Pipelines, Computer architecture, Streaming media, Video Processing BibRef

Breitenstein, M.D., Sommerlade, E., Leibe, B., Van Gool, L.J., Reid, I.D.,
Probabilistic Parameter Selection for Learning Scene Structure from Video,
BMVC08(xx-yy).
PDF File. 0809
BibRef

Tagawa, N.[Norio], Kawaguchi, J.[Junya], Naganuma, S.[Shoichi], Okubo, K.[Kan],
Direct 3-D shape recovery from image sequence based on multi-scale Bayesian network,
ICPR08(1-4).
IEEE DOI 0812
BibRef

Sun, Y., Bayoumi, M.M.,
A simple feedforward neural network architecture for 3-D motion and structure estimation,
ICIP96(III: 783-786).
IEEE DOI 9610
BibRef

Chapter on Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion continues in
Hand-Held Camera Reconstruction, Phone Based Reconstruction, Shape from Motion .


Last update:Mar 16, 2024 at 20:36:19