9.8.1 Single View 3D Reconstruction, Learning

Chapter Contents (Back)
Single View.

Choi, S.H.[Sung-Hwan], Min, D.B.[Dong-Bo], Ham, B.[Bumsub], Kim, Y.J.[Young-Jung], Oh, C.[Changjae], Sohn, K.H.[Kwang-Hoon],
Depth Analogy: Data-Driven Approach for Single Image Depth Estimation Using Gradient Samples,
IP(24), No. 12, December 2015, pp. 5953-5966.
IEEE DOI 1512
Poisson distribution BibRef

Kim, Y.J.[Young-Jung], Min, D.B.[Dong-Bo], Ham, B.[Bumsub], Sohn, K.H.[Kwang-Hoon],
Fast Domain Decomposition for Global Image Smoothing,
IP(26), No. 8, August 2017, pp. 4079-4091.
IEEE DOI 1707
concave programming, decomposition, least squares approximations, minimisation, computational photography application, edge-preserving smoothing, BibRef

Kim, Y.J.[Young-Jung], Jung, H., Min, D.B.[Dong-Bo], Sohn, K.H.[Kwang-Hoon],
Deeply Aggregated Alternating Minimization for Image Restoration,
CVPR17(284-292)
IEEE DOI 1711
Algorithm design and analysis, Data models, Image reconstruction, Image restoration, Minimization, Neural networks, Optimization BibRef

Kim, S.[Sunok], Choi, S.H.[Sung-Hwan], Sohn, K.H.[Kwang-Hoon],
Learning depth from a single image using visual-depth words,
ICIP15(1895-1899)
IEEE DOI 1512
K-means clustering BibRef

Kim, Y.J.[Young-Jung], Choi, S.H.[Sung-Hwan], Sohn, K.H.[Kwang-Hoon],
Data-driven single image depth estimation using weighted median statistics,
ICIP14(3808-3812)
IEEE DOI 1502
Based on matches to similar images. Wrong section, one of several, learn patterns from other images, apply. BibRef

Herrera, J.L.[Jose L.], del-Bianco, C.R.[Carlos R.], García, N.[Narciso],
Automatic Depth Extraction from 2D Images Using a Cluster-Based Learning Framework,
IP(27), No. 7, July 2018, pp. 3288-3299.
IEEE DOI 1805
BibRef
Earlier:
Learning 3D structure from 2D images using LBP features,
ICIP14(2022-2025)
IEEE DOI 1502
feature extraction, image colour analysis, image convertors, image filtering, image representation, image segmentation, machine learning BibRef

Herrera, J.L.[Jose L.], Konrad, J.[Janusz], del-Bianco, C.R.[Carlos R.], Garcia, N.[Narciso],
Learning-based depth estimation from 2D images using GIST and saliency,
ICIP15(4753-4757)
IEEE DOI 1512
2D-to-3D Image Conversion; Depth maps; GIST Descriptor; Saliency. Color BibRef

Zhang, Z., Xu, C., Yang, J., Gao, J., Cui, Z.,
Progressive Hard-Mining Network for Monocular Depth Estimation,
IP(27), No. 8, August 2018, pp. 3691-3702.
IEEE DOI 1806
computer vision, data mining, estimation theory, feature extraction, image colour analysis, image resolution, recursive learning BibRef

He, L., Wang, G., Hu, Z.,
Learning Depth From Single Images With Deep Neural Network Embedding Focal Length,
IP(27), No. 9, September 2018, pp. 4676-4689.
IEEE DOI 1807
Markov processes, image processing, learning (artificial intelligence), neural nets, single images BibRef

Ren, X.Y.[Xiao-Yuan], Jiang, L.B.[Li-Bing], Tang, X.A.[Xiao-An], Zhang, J.[Junda],
Single-Image 3D Pose Estimation for Texture-Less Object via Symmetric Prior,
IEICE(E101-D), No. 7, July 2018, pp. 1972-1975.
WWW Link. 1807
BibRef

Bostan, E., Kamilov, U.S., Waller, L.,
Learning-Based Image Reconstruction via Parallel Proximal Algorithm,
SPLetters(25), No. 7, July 2018, pp. 989-993.
IEEE DOI 1807
image reconstruction, iterative methods, learning (artificial intelligence), parallel algorithms, statistical modeling BibRef

Zhang, Z.Y.[Zhen-Yu], Xu, C.Y.[Chun-Yan], Yang, J.[Jian], Tai, Y.[Ying], Chen, L.[Liang],
Deep hierarchical guidance and regularization learning for end-to-end depth estimation,
PR(83), 2018, pp. 430-442.
Elsevier DOI 1808
Depth estimation, Multi-regularization, Deep neural network BibRef

Hou, B., Khanal, B., Alansary, A., McDonagh, S., Davidson, A., Rutherford, M., Hajnal, J.V., Rueckert, D., Glocker, B., Kainz, B.,
3-D Reconstruction in Canonical Co-Ordinate Space From Arbitrarily Oriented 2-D Images,
MedImg(37), No. 8, August 2018, pp. 1737-1750.
IEEE DOI 1808
Image reconstruction, Manuals, Robustness, image registration BibRef

Cao, Y., Wu, Z., Shen, C.,
Estimating Depth From Monocular Images as Classification Using Deep Fully Convolutional Residual Networks,
CirSysVideo(28), No. 11, November 2018, pp. 3174-3182.
IEEE DOI 1811
Estimation, Training, Semantics, Network architecture, Predictive models, Neural networks, Probability distribution, depth estimation BibRef

Santos, R.[Roi], Pardo, X.M.[Xose M.], Fdez-Vidal, X.R.[Xose R.],
Scene wireframes sketching for Unmanned Aerial Vehicles,
PR(86), 2019, pp. 354-367.
Elsevier DOI 1811
3D abstraction, Reconstruction, Line-based sketching, UAV BibRef


Chen, Z.[Zhao], Badrinarayanan, V.[Vijay], Drozdov, G.[Gilad], Rabinovich, A.[Andrew],
Estimating Depth from RGB and Sparse Sensing,
ECCV18(II: 176-192).
Springer DOI 1810
BibRef

Jiang, L.[Li], Shi, S.[Shaoshuai], Qi, X.J.[Xiao-Juan], Jia, J.Y.[Jia-Ya],
GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction,
ECCV18(VIII: 820-834).
Springer DOI 1810
BibRef

de La Garanderie, G.P.[Grégoire Payen], Abarghouei, A.A.[Amir Atapour], Breckon, T.P.[Toby P.],
Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery,
ECCV18(XIII: 812-830).
Springer DOI 1810
BibRef

Clark, R.[Ronald], Bloesch, M.[Michael], Czarnowski, J.[Jan], Leutenegger, S.[Stefan], Davison, A.J.[Andrew J.],
Learning to Solve Nonlinear Least Squares for Monocular Stereo,
ECCV18(VIII: 291-306).
Springer DOI 1810
BibRef

Heo, M.[Minhyeok], Lee, J.[Jaehan], Kim, K.R.[Kyung-Rae], Kim, H.U.[Han-Ul], Kim, C.S.[Chang-Su],
Monocular Depth Estimation Using Whole Strip Masking and Reliability-Based Refinement,
ECCV18(II: 39-55).
Springer DOI 1810
BibRef

Zhong, Y.R.[Yi-Ran], Dai, Y.C.[Yu-Chao], Li, H.D.[Hong-Dong],
Stereo Computation for a Single Mixture Image,
ECCV18(IX: 441-456).
Springer DOI 1810
BibRef

Huang, S.Y.[Si-Yuan], Qi, S.Y.[Si-Yuan], Zhu, Y.X.[Yi-Xin], Xiao, Y.[Yinxue], Xu, Y.[Yuanlu], Zhu, S.C.[Song-Chun],
Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image,
ECCV18(VII: 194-211).
Springer DOI 1810
BibRef

Yang, F.T.[Feng-Ting], Zhou, Z.[Zihan],
Recovering 3D Planes from a Single Image via Convolutional Neural Networks,
ECCV18(X: 87-103).
Springer DOI 1810
BibRef

Jiao, J.B.[Jian-Bo], Cao, Y.[Ying], Song, Y.B.[Yi-Bing], Lau, R.[Rynson],
Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss,
ECCV18(XV: 55-71).
Springer DOI 1810
BibRef

Guo, X.Y.[Xiao-Yang], Li, H.S.[Hong-Sheng], Yi, S.[Shuai], Ren, J.[Jimmy], Wang, X.G.[Xiao-Gang],
Learning Monocular Depth by Distilling Cross-Domain Stereo Networks,
ECCV18(XI: 506-523).
Springer DOI 1810
BibRef

Wang, N.Y.[Nan-Yang], Zhang, Y.[Yinda], Li, Z.W.[Zhu-Wen], Fu, Y.W.[Yan-Wei], Liu, W.[Wei], Jiang, Y.G.[Yu-Gang],
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images,
ECCV18(XI: 55-71).
Springer DOI 1810
BibRef

Gan, Y.K.[Yu-Kang], Xu, X.Y.[Xiang-Yu], Sun, W.X.[Wen-Xiu], Lin, L.[Liang],
Monocular Depth Estimation with Affinity, Vertical Pooling, and Label Enhancement,
ECCV18(III: 232-247).
Springer DOI 1810
BibRef

Zheng, C.X.[Chuan-Xia], Cham, T.J.[Tat-Jen], Cai, J.F.[Jian-Fei],
T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks,
ECCV18(VII: 798-814).
Springer DOI 1810
BibRef

Yang, G.[Guandao], Cui, Y.[Yin], Belongie, S.[Serge], Hariharan, B.[Bharath],
Learning Single-View 3D Reconstruction with Limited Pose Supervision,
ECCV18(XV: 90-105).
Springer DOI 1810
BibRef

Wu, J.J.[Jia-Jun], Zhang, C.K.[Cheng-Kai], Zhang, X.M.[Xiu-Ming], Zhang, Z.T.[Zhou-Tong], Freeman, W.T.[William T.], Tenenbaum, J.B.[Joshua B.],
Learning Shape Priors for Single-View 3D Completion And Reconstruction,
ECCV18(XI: 673-691).
Springer DOI 1810
BibRef

Jayaraman, D.[Dinesh], Gao, R.[Ruohan], Grauman, K.[Kristen],
ShapeCodes: Self-supervised Feature Learning by Lifting Views to Viewgrids,
ECCV18(XVI: 126-144).
Springer DOI 1810
BibRef

Cheng, X.J.[Xin-Jing], Wang, P.[Peng], Yang, R.G.[Rui-Gang],
Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network,
ECCV18(XVI: 108-125).
Springer DOI 1810
BibRef

Carvalho, M., Saux, B.L., Trouvé-Peloux, P., Almansa, A., Champagnat, F.,
On Regression Losses for Deep Depth Estimation,
ICIP18(2915-2919)
IEEE DOI 1809
Estimation, Training, Standards, Convolution, Machine learning, Network architecture, Depth estimation, loss function BibRef

da Silveira, T.L.T., Dal'aqua, L.P., Jung, C.R.,
Indoor Depth Estimation from Single Spherical Images,
ICIP18(2935-2939)
IEEE DOI 1809
Estimation, Cameras, Distortion, Image color analysis, Training, Convolutional neural networks, Solid modeling, Spherical images, BibRef

Moukari, M., Picard, S., Simoni, L., Jurie, F.,
Deep Multi-Scale Architectures for Monocular Depth Estimation,
ICIP18(2940-2944)
IEEE DOI 1809
Training, Estimation, Decoding, Computer architecture, Semantics, Spatial resolution, Task analysis, monocular depth estimation, CNN architecture BibRef

Huang, J.[Jun], Bi, T.T.[Tian-Teng], Liu, Y.[Yue], Wang, Y.T.[Yong-Tian],
Stereo Generation from a Single Image Using Deep Residual Network,
ICIP18(3653-3657)
IEEE DOI 1809
Painting, Training, Interpolation, Measurement, Stereo image processing, Image edge detection, layered images BibRef

Chang, Y., Li, S., Han, X., Hou, C.,
Cyclopean Image Based Stereoscopic Image Quality Assessment by Using Sparse Representation,
ICIP18(2825-2829)
IEEE DOI 1809
Image color analysis, Stereo image processing, Image reconstruction, Feature extraction, Entropy, Dictionaries, entropy BibRef

Tian, H., Li, F.,
Depth Prediction From a Single Image with 3D Consistency,
ICIP18(111-115)
IEEE DOI 1809
Image color analysis, Training, Distortion, Color, Computer architecture, Solid modeling, random projection BibRef

Kurenkov, A., Ji, J., Garg, A., Mehta, V., Gwak, J., Choy, C., Savarese, S.,
DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image,
WACV18(858-866)
IEEE DOI 1806
CAD, augmented reality, computer vision, image reconstruction, learning (artificial intelligence), object recognition, BibRef

Nimisha, T.M., Mathamkode, A.[Arun], Ambasamudram, R.[Rajagopalan],
Dictionary Replacement for Single Image Restoration of 3D Scenes,
BMVC16(xx-yy).
HTML Version. 1805
BibRef

Yao, Q., Luo, G., Zhu, Y.,
Depth estimation for outdoor image using couple dictionary learning and region detection,
VCIP17(1-4)
IEEE DOI 1804
computer vision, edge detection, image representation, image retrieval, learning (artificial intelligence), single image depth estimation BibRef

Jung, H., Kim, Y., Min, D., Oh, C., Sohn, K.,
Depth prediction from a single image with conditional adversarial networks,
ICIP17(1717-1721)
IEEE DOI 1803
Databases, Estimation, Generators, Periodic structures, Spatial resolution, Training, Depth from a single image, generative adversarial learning BibRef

Guo, X., Nguyen, K., Denman, S., Fookes, C., Sridharan, S.,
Single image depth prediction using super-column super-pixel features,
ICIP17(2657-2661)
IEEE DOI 1803
Error analysis, Feature extraction, Image color analysis, Image segmentation, Interpolation, Task analysis, Training, depth, super pixel BibRef

Chen, Y., Wang, F., Wang, X.,
Recovering complex non-rigid 3D structures from monocular images by union of nonlinear subspaces,
ICIP17(2622-2626)
IEEE DOI 1803
Cameras, Kernel, Radio frequency, Shape, Trajectory, subspace clustering BibRef

Johnston, A., Garg, R., Carneiro, G., Reid, I.D.[Ian D.],
Scaling CNNs for High Resolution Volumetric Reconstruction from a Single Image,
DeepLearn-G17(930-939)
IEEE DOI 1802
Convolution, Deconvolution, Discrete cosine transforms, Image reconstruction, Shape, Solid modeling, Training BibRef

Romaszko, L., Williams, C.K.I., Moreno, P., Kohli, P.,
Vision-as-Inverse-Graphics: Obtaining a Rich 3D Explanation of a Scene from a Single Image,
DeepLearn-G17(940-948)
IEEE DOI 1802
Cameras, Detectors, Graphics, Lighting, Object detection, Probabilistic logic, Transforms BibRef

Li, J., Klein, R., Yao, A.,
A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images,
ICCV17(3392-3400)
IEEE DOI 1802
image colour analysis, learning (artificial intelligence), NYU, NYU Depth, accurate depth map, deep learning methods, Training BibRef

Li, X., Jie, Z., Wang, W., Liu, C., Yang, J., Shen, X., Lin, Z., Chen, Q., Yan, S., Feng, J.,
FoveaNet: Perspective-Aware Urban Scene Parsing,
ICCV17(784-792)
IEEE DOI 1802
geometry, image recognition, neural nets, object detection, object recognition, FoveaNet model, BibRef

Zhu, R.[Rui], Galoogahi, H.K.[Hamed Kiani], Wang, C.Y.[Chao-Yang], Lucey, S.[Simon],
Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction from a Single Image,
ICCV17(57-65)
IEEE DOI 1802
computer vision, image classification, image reconstruction, learning (artificial intelligence), object detection, BibRef

Mohaghegh, H., Karimi, N., Soroushmehr, S.M.R., Samavi, S., Najarian, K.,
Single image depth estimation using joint local-global features,
ICPR16(727-732)
IEEE DOI 1705
Monocular depth cues. Correlation, Databases, Estimation, Solid modeling, Three-dimensional displays, Training, Two dimensional displays, Data-driven approaches, Depth estimation, Joint local-global framework, KNN regression model. BibRef

Baig, M.H.[Mohammad Haris], Torresani, L.[Lorenzo],
Coupled depth learning,
WACV16(1-10)
IEEE DOI 1606
Computational modeling. Depth from single image via learning. BibRef

Akhmadeev, F.[Foat],
Surface Prediction for a Single Image of Urban Scenes,
AutoSystems14(369-382).
Springer DOI 1504
BibRef

Ikeoka, H.[Hiroshi], Murata, T.[Takafumi], Okuwaki, M.[Maiki], Hamamoto, T.[Takayuki],
Depth estimation for automotive with tilted optics imaging,
ICIP14(3852-3856)
IEEE DOI 1502
Automotive engineering BibRef

Hua, Y., Tian, H., Cai, A., Shi, P.,
Cross-modal correlation learning with deep convolutional architecture,
VCIP15(1-4)
IEEE DOI 1605
Analytical models BibRef

Tian, H.[Hu], Zhuang, B.[Bojin], Hua, Y.[Yan], Cai, A.[Anni],
Depth inference with convolutional neural network,
VCIP14(169-172)
IEEE DOI 1504
BibRef
Earlier:
Depth extraction from a single image by sampling based on distance metric learning,
ICIP14(2017-2021)
IEEE DOI 1502
feature extraction. Estimation. Mahalanobis distance rather than Euclidean distance between images. depth fusion. BibRef

Li, H.S.[Hong-Song], Song, T.[Ting], Wu, Z.H.[Ze-Huan], Ma, J.D.[Jian-Dong], Ding, G.[Gangyi],
Reconstruction of a Complex Mirror Surface from a Single Image,
ISVC14(I: 402-412).
Springer DOI 1501
Use the multiple reflections of same environment point. BibRef

Liu, M.M.[Miao-Miao], Salzmann, M.[Mathieu], He, X.M.[Xu-Ming],
Discrete-Continuous Depth Estimation from a Single Image,
CVPR14(716-723)
IEEE DOI 1409
BibRef

Visa, G.P.[Guillem Palou], Salembier, P.[Philippe],
Precision-Recall-Classification Evaluation Framework: Application to Depth Estimation on Single Images,
ECCV14(I: 648-662).
Springer DOI 1408
depth ordering on single images. Segment then order. BibRef

Cheng, H.M.[Hsin-Min], Tseng, C.Y.[Chen-Yu], Hsin, C.H.[Cheng-Ho], Wang, S.J.[Sheng-Jyh],
Single-image 3-D depth estimation for urban scenes,
ICIP13(2121-2125)
IEEE DOI 1402
3-D depth recovery;Depth estimation BibRef

Chapter on 3-D Shape from X -- Shading, Textures, Lasers, Structured Light, Focus, Line Drawings continues in
Three-Dimensional Reconstruction from Different Views .


Last update:Nov 17, 2018 at 09:12:27