1. Home
  2. Proceedings
  3. 3DV
  4. 3DV 2018
Default Cover Image

2018 International Conference on 3D Vision (3DV)

Sept. 5 2018 to Sept. 8 2018

Verona, Italy

Table of Contents

[Title page i]Freely available from IEEE.pp. 1-1
[Title page iii]Freely available from IEEE.pp. 3-3
[Copyright notice]Freely available from IEEE.pp. 4-4
Table of contentsFreely available from IEEE.pp. 5-12
Message from General ChairsFreely available from IEEE.pp. 13-13
Message from Program ChairsFreely available from IEEE.pp. 14-14
Organizing CommitteeFreely available from IEEE.pp. 15-15
ReviewersFreely available from IEEE.pp. 16-16
Emergency ReviewersFreely available from IEEE.pp. 17-17
SponsorsFreely available from IEEE.pp. 18-18
SupportersFreely available from IEEE.pp. 19-19
Keep it Unreal: Bridging the Realism Gap for 2.5D Recognition with Geometry Priors OnlyFull-text access may be available. Sign in or learn about subscription options.pp. 1-11
by Sergey Zakharov, Benjamin Planche, Ziyan Wu, Andreas Hutter, Harald Kosch, Slobodan Ilic
Surface Light Field FusionFull-text access may be available. Sign in or learn about subscription options.pp. 12-21
by Jeong Joon Park, Richard Newcombe, Steve Seitz
Joint Material and Illumination Estimation from Photo Sets in the WildFull-text access may be available. Sign in or learn about subscription options.pp. 22-31
by Tuanfeng Y. Wang, Tobias Ritschel, Niloy J. Mitra
Fusion++: Volumetric Object-Level SLAMFull-text access may be available. Sign in or learn about subscription options.pp. 32-41
by John Mccormac, Ronald Clark, Michael Bloesch, Andrew Davison, Stefan Leutenegger
Patch-Based Non-rigid 3D Reconstruction from a Single Depth StreamFull-text access may be available. Sign in or learn about subscription options.pp. 42-51
by Carmel Kozlov, Miroslava Slavcheva, Slobodan Ilic
Sparse and Dense Data with CNNs: Depth Completion and Semantic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 52-60
by Maximilian Jaritz, Raoul De Charette, Emilie Wirbel, Xavier Perrotton, Fawzi Nashashibi
Multi-scale CNN Stereo and Pattern Removal Technique for Underwater Active Stereo SystemFull-text access may be available. Sign in or learn about subscription options.pp. 61-70
by Kazuto Ichimaru, Ryo Furukawa, Hiroshi Kawasaki
A Multi-resolution Approach for Color Correction of Textured MeshesFull-text access may be available. Sign in or learn about subscription options.pp. 71-78
by Mohammad Rouhani, Matthieu Fradet, Caroline Baillard
Progressive Large-Scale Structure-from-Motion with Orthogonal MSTsFull-text access may be available. Sign in or learn about subscription options.pp. 79-88
by Hainan Cui, Shuhan Shen, Wei Gao, Zhiheng Wang
Multi-scale Direct Sparse Visual Odometry for Large-Scale Natural EnvironmentFull-text access may be available. Sign in or learn about subscription options.pp. 89-97
by Xiaolong Wu, Cedric Pradalier
Detailed Human Avatars from Monocular VideoFull-text access may be available. Sign in or learn about subscription options.pp. 98-109
by Thiemo Alldieck, Marcus Magnor, Weipeng Xu, Christian Theobalt, Gerard Pons-Moll
DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic DepthFull-text access may be available. Sign in or learn about subscription options.pp. 110-119
by Jameel Malik, Ahmed Elhayek, Fabrizio Nunnari, Kiran Varanasi, Kiarash Tamaddon, Alexis Heloir, Didier Stricker
Single-Shot Multi-person 3D Pose Estimation from Monocular RGBFull-text access may be available. Sign in or learn about subscription options.pp. 120-130
by Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller, Weipeng Xu, Srinath Sridhar, Gerard Pons-Moll, Christian Theobalt
Reconstruction of Interior Walls from Point Cloud Data with Min-Hashed J-LinkageFull-text access may be available. Sign in or learn about subscription options.pp. 131-139
by Luca Magri, Andrea Fusiello
Structure-Aware Shape SynthesisFull-text access may be available. Sign in or learn about subscription options.pp. 140-149
by Elena Balashova, Vivek Singh, Jiangping Wang, Brian Teixeira, Terrence Chen, Thomas Funkhouser
Learning Material-Aware Local Descriptors for 3D ShapesFull-text access may be available. Sign in or learn about subscription options.pp. 150-159
by Hubert Lin, Melinos Averkiou, Evangelos Kalogerakis, Balazs Kovacs, Siddhant Ranade, Vladimir Kim, Siddhartha Chaudhuri, Kavita Bala
Joint Representation of Primitive and Non-primitive Objects for 3D VisionFull-text access may be available. Sign in or learn about subscription options.pp. 160-169
by Christiane Sommer, Daniel Cremers
Joint Alignment of Multiple Generalized Point Sets with Anisotropic Positional Uncertainty Based on Expectation MaximizationFull-text access may be available. Sign in or learn about subscription options.pp. 170-179
by Zhe Min, Max Q.-H. Meng
Iterative Global Similarity Points: A Robust Coarse-to-Fine Integration Solution for Pairwise 3D Point Cloud RegistrationFull-text access may be available. Sign in or learn about subscription options.pp. 180-189
by Yue Pan, Bisheng Yang, Fuxun Liang, Zhen Dong
SegmentedFusion: 3D Human Body Reconstruction Using Stitched Bounding BoxesFull-text access may be available. Sign in or learn about subscription options.pp. 190-198
by Shih Hsuan Yao, Diego Thomas, Akihiro Sugimoto, Shang-Hong Lai, Rin-Ichiro Taniguchi Kyushu
Learning to Estimate Indoor Lighting from 3D ObjectsFull-text access may be available. Sign in or learn about subscription options.pp. 199-207
by Henrique Weber, Donald Prévost, Jean-Francois Lalonde
Camera Orientation Estimation in Natural Scenes Using Semantic CuesFull-text access may be available. Sign in or learn about subscription options.pp. 208-217
by Jan Brejcha, Martin Cadík
Four- and Seven-Point Relative Camera Pose from Oriented FeaturesFull-text access may be available. Sign in or learn about subscription options.pp. 218-227
by Steven Mills
UnrealStereo: Controlling Hazardous Factors to Analyze Stereo VisionFull-text access may be available. Sign in or learn about subscription options.pp. 228-237
by Yi Zhang, Weichao Qiu, Qi Chen, Xiaolin Hu, Alan Yuille
RecResNet: A Recurrent Residual CNN Architecture for Disparity Map EnhancementFull-text access may be available. Sign in or learn about subscription options.pp. 238-247
by Konstantinos Batsos, Philippos Mordohai
MVDepthNet: Real-Time Multiview Depth Estimation Neural NetworkFull-text access may be available. Sign in or learn about subscription options.pp. 248-257
by Kaixuan Wang, Shaojie Shen
Cross-Domain Image-Based 3D Shape Retrieval by View Sequence LearningFull-text access may be available. Sign in or learn about subscription options.pp. 258-266
by Tang Lee, Yen-Liang Lin, Hungyueh Chiang, Ming-Wei Chiu, Winston Hsu, Polly Huang
SeeThrough: Finding Objects in Heavily Occluded Indoor Scene ImagesFull-text access may be available. Sign in or learn about subscription options.pp. 267-276
by Niloy J. Mitra, Vladimir Kim, Ersin Yumer, Moos Hueting, Nathan Carr, Pradyumna Reddy
Robust Fitting of Subdivision Surfaces for Smooth Shape AnalysisFull-text access may be available. Sign in or learn about subscription options.pp. 277-285
by Virginia Estellers, Frank Schmidt, Daniel Cremers
Calibrating Light-Field Cameras Using Plenoptic Disc FeaturesFull-text access may be available. Sign in or learn about subscription options.pp. 286-294
by Sean O'brien, Jochen Trumpf, Viorela Ila, Robert Mahony
Unsupervised Depth Estimation from Light Field Using a Convolutional Neural NetworkFull-text access may be available. Sign in or learn about subscription options.pp. 295-303
by Jiayong Peng, Zhiwei Xiong, Dong Liu, Xuejin Chen
Detail Preserving Depth Estimation from a Single Image Using Attention Guided NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 304-313
by Zhixiang Hao, Yu Li, Shaodi You, Feng Lu
Structured Adversarial Training for Unsupervised Monocular Depth EstimationFull-text access may be available. Sign in or learn about subscription options.pp. 314-323
by Ishit Mehta, Parikshit Sakurikar, P. J. Narayanan
Learning Monocular Depth Estimation with Unsupervised Trinocular AssumptionsFull-text access may be available. Sign in or learn about subscription options.pp. 324-333
by Matteo Poggi, Fabio Tosi, Stefano Mattoccia
Human-Centric Scene Understanding from Single View 360 VideoFull-text access may be available. Sign in or learn about subscription options.pp. 334-342
by Sam Fowler, Hansung Kim, Adrian Hilton
Constant Velocity 3D ConvolutionFull-text access may be available. Sign in or learn about subscription options.pp. 343-351
by Yusuke Sekikawa, Kohta Ishikawa, Kosuke Hara, Yuuichi Yoshida, Koichiro Suzuki, Ikuro Sato, Hideo Saito
FEATS: Synthetic Feature Tracks for Structure from Motion EvaluationFull-text access may be available. Sign in or learn about subscription options.pp. 352-361
by Joseph Degol, Jae Yong Lee, Rajbir Kataria, Daniel Yuan, Timothy Bretl, Derek Hoiem
An Image-Based Approach for 3D Reconstruction of Urban Scenes Using Architectural SymmetriesFull-text access may be available. Sign in or learn about subscription options.pp. 362-370
by Natesh Srinivasan, Frank Dellaert
Spatiotemporal Modeling for Efficient Registration of Dynamic 3D FacesFull-text access may be available. Sign in or learn about subscription options.pp. 371-380
by Victoria Fernandez Abrevaya, Stefanie Wuhrer, Edmond Boyer
Survey of Higher Order Rigid Body Motion Interpolation Methods for Keyframe Animation and Continuous-Time Trajectory EstimationFull-text access may be available. Sign in or learn about subscription options.pp. 381-389
by Adrian Haarbach, Tolga Birdal, Slobodan Ilic
Semantic Classification of 3D Point Clouds with Multiscale Spherical NeighborhoodsFull-text access may be available. Sign in or learn about subscription options.pp. 390-398
by Hugues Thomas, François Goulette, Jean-Emmanuel Deschaud, Beatriz Marcotegui, Yann LeGall
Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point CloudsFull-text access may be available. Sign in or learn about subscription options.pp. 399-408
by Chris Zhang, Wenjie Luo, Raquel Urtasun
Logistic Regression of Point Matches for Accurate Transformation EstimationFull-text access may be available. Sign in or learn about subscription options.pp. 409-417
by Yonghuai Liu, Yitian Zhao, Yanquan Zhou, Yongjun Wang, Wei Huang, Jiwan Han, Wanneng Yang, Yiguang Liu Liu
Analyzing Body Fat from Depth ImagesFull-text access may be available. Sign in or learn about subscription options.pp. 418-425
by Marco Carletti, Marco Cristani, Valentina Cavedon, Chiara Milanese, Carlo Zancanaro, Andrea Giachetti
Adversarial Semantic Scene Completion from a Single Depth ImageFull-text access may be available. Sign in or learn about subscription options.pp. 426-434
by Yida Wang, David Joseph Tan, Nassir Navab, Federico Tombari
3DTNet: Learning Local Features Using 2D and 3D CuesFull-text access may be available. Sign in or learn about subscription options.pp. 435-443
by Xiaoxia Xing, Yinghao Cai, Tao Lu, Shaojun Cai, Yiping Yang, Dayong Wen
Structured Low-Rank Matrix Factorization for Point-Cloud DenoisingFull-text access may be available. Sign in or learn about subscription options.pp. 444-453
by Kripasindhu Sarkar, Florian Bernard, Kiran Varanasi, Christian Theobalt, Didier Stricker
Generative Adversarial Frontal View to Bird View SynthesisFull-text access may be available. Sign in or learn about subscription options.pp. 454-463
by Xinge Zhu, Zhichao Yin, Jianping Shi, Hongsheng Li, Dahua Lin
Multi-view Inpainting for RGB-D SequenceFull-text access may be available. Sign in or learn about subscription options.pp. 464-473
by Feiran Li, Gustavo Alfonso Garcia Ricardez, Jun Takamatsu, Tsukasa Ogasawara
Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion CaptureFull-text access may be available. Sign in or learn about subscription options.pp. 474-483
by Denis Tome, Matteo Toso, Lourdes Agapito, Chris Russell
Neural Body Fitting: Unifying Deep Learning and Model Based Human Pose and Shape EstimationFull-text access may be available. Sign in or learn about subscription options.pp. 484-494
by Mohamed Omran, Christoph Lassner, Gerard Pons-Moll, Peter Gehler, Bernt Schiele
3DBodyTex: Textured 3D Body DatasetFull-text access may be available. Sign in or learn about subscription options.pp. 495-504
by Alexandre Saint, Eman Ahmed, Abd El Rahman Shabayek, Kseniya Cherenkova, Gleb Gusev, Djamila Aouada, Bjorn Ottersten
3D Head Pose Estimation Using Tensor Decomposition and Non-linear Manifold ModelingFull-text access may be available. Sign in or learn about subscription options.pp. 505-513
by Dmytro Derkach, Adria Ruiz, Federico Sukno
Hybrid Skeleton Driven Surface Registration for Temporally Consistent Volumetric VideoFull-text access may be available. Sign in or learn about subscription options.pp. 514-522
by Joao Regateiro, Marco Volino, Adrian Hilton
Fine-Level Semantic Labeling of Large-Scale 3D Model by Active LearningFull-text access may be available. Sign in or learn about subscription options.pp. 523-532
by Yang Zhou, Shuhan Shen, Zhanyi Hu
Plane-Based Optimization of Geometry and Texture for RGB-D Reconstruction of Indoor ScenesFull-text access may be available. Sign in or learn about subscription options.pp. 533-541
by Chao Wang, Xiaohu Guo
Learning a Hierarchical Latent-Variable Model of 3D ShapesFull-text access may be available. Sign in or learn about subscription options.pp. 542-551
by Shikun Liu, Lee Giles, Alexander Ororbia
The Double Sphere Camera ModelFull-text access may be available. Sign in or learn about subscription options.pp. 552-560
by Vladyslav Usenko, Nikolaus Demmel, Daniel Cremers
DSR: Direct Self-Rectification for Uncalibrated Dual-Lens CamerasFull-text access may be available. Sign in or learn about subscription options.pp. 561-569
by Ruichao Xiao, Wenxiu Sun, Jiahao Pang, Qiong Yan, Jimmy Ren
Monocular Depth Estimation via Deep Structured Models with Ordinal ConstraintsFull-text access may be available. Sign in or learn about subscription options.pp. 570-577
by Daniel Ron, Kun Duan, Chongyang Ma, Ning Xu, Shenlong Wang, Sumant Hanumante, Dhritiman Sagar
ESPReSSo: Efficient Slanted PatchMatch for Real-Time Spacetime StereoFull-text access may be available. Sign in or learn about subscription options.pp. 578-586
by Harris Nover, Supreeth Achar, Dan Goldman
Unsupervised Adversarial Depth Estimation Using Cycled Generative NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 587-595
by Andrea Pilzer, Dan Xu, Mihai Puscas, Elisa Ricci, Nicu Sebe
TwinFusion: High Framerate Non-rigid Fusion through Fast Correspondence TrackingFull-text access may be available. Sign in or learn about subscription options.pp. 596-605
by Kaiwen Guo, Jonathan Taylor, Sean Fanello, Andrea Tagliasacchi, Mingsong Dou, Philip Davidson, Adarsh Kowdle, Shahram Izadi
Learning to Reconstruct Texture-Less Deformable Surfaces from a Single ViewFull-text access may be available. Sign in or learn about subscription options.pp. 606-615
by Jan Bednarik, Pascal Fua, Mathieu Salzmann
Multi-planar Monocular Reconstruction of Manhattan Indoor ScenesFull-text access may be available. Sign in or learn about subscription options.pp. 616-624
by Seongdo Kim, Roberto Manduchi, Siyang Qin
Novel Single View Constraints for Manhattan 3D Line ReconstructionFull-text access may be available. Sign in or learn about subscription options.pp. 625-633
by Siddhant Ranade, Srikumar Ramalingam
Learning to Generate Facial Depth MapsFull-text access may be available. Sign in or learn about subscription options.pp. 634-642
by Stefano Pini, Filippo Grazioli, Guido Borghi, Roberto Vezzani, Rita Cucchiara
Accurate Sparse Feature Regression Forest Learning for Real-Time Camera RelocalizationFull-text access may be available. Sign in or learn about subscription options.pp. 643-652
by Nam-Duong Duong, Amine Kacete, Catherine Soladie, Pierre-Yves Richard, Jérome Royan
ACE: An Efficient Asynchronous Corner Tracker for Event CamerasFull-text access may be available. Sign in or learn about subscription options.pp. 653-661
by Ignacio Alzugaray, Margarita Chli
A Data-Driven Prior on Facet Orientation for Semantic Mesh LabelingFull-text access may be available. Sign in or learn about subscription options.pp. 662-671
by Andrea Romanoni, Matteo Matteucci
Parsing Geometry Using Structure-Aware Shape TemplatesFull-text access may be available. Sign in or learn about subscription options.pp. 672-681
by Vignesh Ganapathi-Subramanian, Olga Diamanti, Soeren Pirk, Chengcheng Tang, Matthias Niessner, Leonidas Guibas
A 3D Coarse-to-Fine Framework for Volumetric Medical Image SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 682-690
by Zhuotun Zhu, Yingda Xia, Wei Shen, Elliot Fishman, Alan Yuille
Deep Learning Parametrization for B-Spline Curve ApproximationFull-text access may be available. Sign in or learn about subscription options.pp. 691-699
by Pascal Laube, Matthias O. Franz, Georg Umlauf
Learning to Align Images Using Weak Geometric SupervisionFull-text access may be available. Sign in or learn about subscription options.pp. 700-709
by Jing Dong, Byron Boots, Frank Dellaert, Ranveer Chandra, Sudipta Sinha
Self Functional MapsFull-text access may be available. Sign in or learn about subscription options.pp. 710-718
by Oshri Halimi, Ron Kimmel
Residual MeshNet: Learning to Deform Meshes for Single-View 3D ReconstructionFull-text access may be available. Sign in or learn about subscription options.pp. 719-727
by Junyi Pan, Jun Li, Xiaoguang Han, Kui Jia
PCN: Point Completion NetworkFull-text access may be available. Sign in or learn about subscription options.pp. 728-737
by Wentao Yuan, Tejas Khot, David Held, Christoph Mertz, Martial Hebert
Weakly Supervised Learning of Indoor Geometry by Dual WarpingFull-text access may be available. Sign in or learn about subscription options.pp. 738-746
by Pulak Purkait, Ujwal Bonde, Christopher Zach
EOE: Expected Overlap Estimation over Unstructured Point Cloud DataFull-text access may be available. Sign in or learn about subscription options.pp. 747-755
by Benjamin Eckart, Kihwan Kim, Kautz Jan
NRGA: Gravitational Approach for Non-rigid Point Set RegistrationFull-text access may be available. Sign in or learn about subscription options.pp. 756-765
by Sk Aziz Ali, Vladislav Golyanik, Didier Stricker
DUGMA: Dynamic Uncertainty-Based Gaussian Mixture AlignmentFull-text access may be available. Sign in or learn about subscription options.pp. 766-774
by Can Pu, Nanbo Li, Radim Tylecek, Bob Fisher
Author indexFreely available from IEEE.pp. 775-779
[Publisher's information]Freely available from IEEE.pp. 780-780
Showing 94 out of 94