Program


Presenter instructions: If you are a presenter (oral or poster session) check here the instructions.


Keynote Speakers

keynote
Wen Gao

Peking University

keynote
Niloy Mitra

University College London (UCL)

keynote
Long Quan

The Hong Kong University of Science and Technology

keynote
Davide Scaramuzza

University of Zurich and ETH Zurich

keynote
Ruigang Yang

Baidu Research

keynote
Zhengyou Zhang

Microsoft Research

Conference Program Overview


Monday, 10/9/2017
10:00 AM - 6:00 PM Register
Tuesday, 10/10/2017
9:00 - 9:15 AM Opening Remarks
9:15 - 10:00 AM Keynote 1: Zhengyou Zhang, "3D Computer Vision for Immersive Interaction and Remote Collaboration"
10:00 - 10:30 AM Coffee Break
10:30 - 11:10 AM Oral Session 1
11:10 - 11:30 AM Spotlight Session 1
11:30 - 12:30 PM Poster session 1
12:30 - 2:00 PM Lunch
2:00 - 2:45 PM Keynote 2: Davide Scaramuzza,"Robust, Visual-Inertial State Estimation: from Frame-based to Event-based Cameras"
2:45 - 3:10 PM Coffee Break
3:10 - 3:50 PM Oral Session 2
3:50 - 5:20 PM Forum: The challenges and opportunities in 3D sensing
5:20 - 6:20 PM Poster session 1
6:20 - 8:20 PM Welcome Reception

Wednesday, 10/11/2017
9:00 - 9:15 AM Announcements
9:15 - 10:00 AM Keynote 3: Wen Gao, "Online visual processing for 3D reconstruction, SLAM, and object recognition"
10:00 - 10:30 AM Coffee Break
10:30 - 11:10 AM Oral Session 3
11:10 - 11:30 AM Spotlight Session 2
11:30 - 12:30 PM Poster session 2
12:30 - 2:00 PM Lunch
2:00 - 2:45 PM Keynote 4: Long Quan, "Computer Vision, Visual Learning, and 3D Reconstruction: Modeling the world with drones and smartphones!"
2:45 - 3:10 PM Coffee Break
3:10 - 3:50 PM Oral Session 4
3:50 - 4:25 PM Spotlight Session 3
4:25 - 5:25 PM Poster session 2
5:30 - 8:00 PM Banquet

Thursday, 10/12/2017
9:00 - 9:15 AM Announcements
9:15 - 10:00 AM Keynote 5: Niloy Mitra, "Building a Factorized Scene Model: Capturing Appearance, Geometry, and Interactions"
10:00 - 10:30 AM Coffee Break
10:30 - 11:10 AM Oral Session 5
11:10 - 11:30 AM Spotlight Session 4
11:30 - 12:30 PM Poster session 3
12:30 - 2:00 PM Lunch
2:00 - 2:45 PM Keynote 6: Ruigang Yang, "3D Vision Research and Applications at Baidu"
2:45 - 3:10 PM Coffee Break
3:10 - 3:50 PM Oral Session 6
3:50 - 4:20 PM Spotlight Session 5
4:20 - 5:20 PM Poster session 3
5:20 - 6:20 PM Awards, Closing Remarks and 3DV-18

Conference Program Details

Oral Session 1

Session Chair: Ping Tan

  • DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition

    Benjamin Planche (Siemens Corp.), Ziyan Wu (Siemens Corp.), Kai Ma (Siemens Healthcare), Shanhui Sun (Siemens Healthineers), Stefan Kluckner (Siemens Healthineers), Oliver Lehmann (Siemens Healthineers), Terrence Chen (Siemens Healthineers), Jan Ernst (Siemens Corp.), Andreas Hutter (Siemens Corp.), Harald Kosch (Univ. of Passau), Sergey Zakharov (Siemens Corp.)

  • Sparsity Invariant CNNs

    Jonas Uhrig (Daimler AG), Nick Schneider (Daimler AG), Lukas Schneider (Daimler), Thomas Brox (Univ. of Freiburg), Andreas Geiger (Max Planck Institute)


Spotlight Session 1

Session Chair: Ping Tan

  • A Novel Self-Calibration Method for a Stereo-ToF System Using a Kinect V2 and Two 4K GoPro Cameras

    Yuan Gao (Kiel University), Sandro Esquivel (Kiel University), Reinhard Koch (Kiel University), Joachim Keinert (Fraunhofer IIS)

  • 4D Temporally Coherent Dynamic Light-field Video

    Armin Mustafa (Univ. of Surrey), Marco Volino (Univ. of Surrey), Jean-Yves Guillemaut (Univ. of Surrey), Adrian Hilton (Univ. of Surrey)

  • NERF: Dynamic High Resolution Deformable Articulated Tracking

    Aaron T Walsman (Univ. of Washington), Tanner Schmidt (Univ. of Washington), Weilin Wan (Univ. of Washington), Dieter Fox (Univ. of Washington)

  • High Dynamic Range SLAM with Map-Aware Exposure Time Control

    Sergey V Alexandrov (TU Wien), Johann Prankl (TU Wien), Michael Zillich (TU Wien), Markus Vincze (TU Wien)


Oral Session 2

Session Chair: Gabriel Taubin

  • OctNetFusion: Learning Depth Fusion from Data

    Gernot Riegler (Graz Univ. of Technology), Ali Osman Ulusoy (Microsoft/Max Planck Institute), Horst Bischof (Graz Univ. of Technology), Andreas Geiger (Max Planck Institute)

  • 3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks

    Zhaoliang Lun (UMass Amherst), Matheus A Gadelha (UMass Amherst), Evangelos Kalogerakis (UMass Amherst), Subhransu Maji (UMass Amherst), Rui Wang (UMass Amherst)


Poster Session 1

  • Scalable Dense Monocular Surface Reconstruction

    Mohammad Dawud Ansari (DFKI), Vladislav Golyanik (DFKI), Didier Stricker (DFKI)

  • Compact Model Representation for 3D Reconstruction

    Jhony Kaesemodel Pontes (CMU), Chen Kong (CMU), Anders Eriksson (QUT), Clinton Fookes (QUT), Sridha Sridharan (QUT), Simon Lucey (CMU)

  • Tracking Radioactive Sources through Sensor Fusion of Omnidirectional LIDAR and Isotropic Rad-detectors

    Kristofer Henderson (Univ. of Florida), Kelsey Stadnikia (Univ. of Florida), Allan Martin (Univ. of Florida), Andreas Enqvist (Univ. of Florida), Koppal Sanjeev (Univ. of Florida)

  • Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles

    Christos Maniatis (Univ. of Edinburgh), Marcelo Saval-Calvo (Univ. of Alicante), Radim Tylecek (Univ. of Edinburgh), Bob Fisher (Univ. of Edinburgh)

  • Continuous Signed Distance Functions for 3D Vision

    Simen Haugo (Norwegian Univ. of Science and Technology)

  • Interactive 3D Modeling with a Generative Adversarial Network

    Jerry J Liu (Princeton University), Fisher Yu (UC Berkeley), Thomas Funkhouser (Princeton University)

  • How to Refine 3D Hand Pose Estimation from Unlabelled Depth Data ?

    Endri Dibra (ETH Zurich), Thomas Wolf (ETH Zurich), Markus Gross (ETH Zurich), Cengiz Oztireli (ETH Zurich)

  • Adversarially Parameterized Optimization for 3D Human Pose Estimation

    Dominic Jack (QUT), Frederic Maire (QUT), Anders Eriksson (QUT), Sareh Shirazi (QUT)

  • GlobalSLAM: Initialization-robust Monocular Visual SLAM

    Chengzhou Tang (Simon Fraser University), Oliver Wang (Adobe), Ping Tan (Simon Fraser University)


Oral Session 3

Session Chair: Jan Michael Frahm

  • GraphMatch: Efficient Large-Scale Graph Construction for Structure from Motion

    Qiaodong Cui (UC Santa Barbara), Victor Fragoso (West Virginia University), Chris Sweeney (Univ. of Washington), Pradeep Sen (UC Santa Barbara)

  • Fast Incremental Bundle Adjustment with Covariance Recovery

    Viorela Ila (ANU), Lukas Polok (Brno Univ. of Technology), Marek Solony (VUT), Klemen Istenic (UDG)


Spotlight Session 2

Session Chair: Jan Michael Frahm

  • Relative Camera Refinement for Accurate Dense Reconstruction

    Yao Yao (HKUST), Shiwei Li (HKUST), Siyu Zhu (HKUST), Tian Fang (HKUST), Hanyu Deng (HKUST), Long Quan (HKUST)

  • Line-based Robust SfM with Little Image Overlap

    Yohann Salaun (LIGM), Renaud Marlet (Ecole des Ponts ParisTech), Pascal Monasse (Ecole des Ponts ParisTech)

  • Batched Incremental Structure-from-Motion

    Hainan Cui (Chinese Academy of Sciences), Shuhan Shen (Chinese Academy of Sciences), Xiang Gao (Chinese Academy of Sciences), Zhanyi Hu (Chinese Academy of Sciences)

  • Semi-Global Stereo Matching with Surface Orientation Prior

    Daniel Scharstein (Middlebury College), Tatsunori Taniai (RIKEN AIP), Sudipta Sinha (Microsoft Research)


Oral Session 4

Session Chair: Adrian Hilton

  • Cascaded Scene Flow Prediction using Semantic Segmentation

    Zhile Ren (Brown University), Deqing Sun (NVIDIA), Kautz Jan (NVIDIA), Erik B Sudderth (UC Irvine)

  • Static and Dynamic Objects Analysis as a 3D Vector Field

    Cansen Jiang (Univ. Bourgogne Franche-Comte), Danda Pani Paudel (ETH Zurich), Yohan Fougerolle (Univ. of Burgundy), David Fofi (Univ. Bourgogne Franche-Comte), Cedric Demonceaux (Univ. Bourgogne Franche-Comte)


Spotlight Session 3

Session Chair: Adrian Hilton

  • Generalized Pose Estimation from Line Correspondences with Known Vertical Direction

    Nora Horanyi (Univ. of Szeged), Zoltan Kato (Univ. of Szeged)

  • The Two Lines Light Source (TLLS)

    Wookyeon Hwang (Brown University), Gabriel Taubin (Brown University)

  • Weakly Supervised 3D Reconstruction with Manifold Constraint

    JunYoung Gwak (Stanford University), Christopher Choy (Stanford University), Manmohan Chandraker (UC San Diego), Animesh Garg (Stanford University), Silvio Savarese (Stanford University)

  • Multiframe Scene Flow with Piecewise Rigid Motion

    Vladislav Golyanik (DFKI), Kihwan Kim (NVIDIA), Robert Maier (TU Munich), Matthias Niessner (TU Munich), Didier Stricker (DFKI), Kautz Jan (NVIDIA)

  • Camera Uncertainty Computation in Large 3D Reconstruction

    Michal Polic (Czech Technical University), Tomas Pajdla (Czech Technical University)

  • Probabilistic Object Reconstruction with Online Loop Closure

    Jack M Hunt (Univ. of Oxford), Victor Prisacariu (Univ. of Oxford), Stuart Golodetz (Univ. of Oxford), Philip Torr (Univ. of Oxford)

  • Multi-Label Point Cloud Annotation by Selection of Sparse Control Points

    Riccardo Monica (Univ. of Parma), Jacopo Aleotti (Univ. of Parma), Michael Zillich (TU Wien), Markus Vincze (TU Wien)


Poster Session 2

  • Controllable Variation Synthesis for Surface Motion Capture

    Adnane Boukhayma (INRIA), Edmond Boyer (INRIA)

  • Variational Building Modeling from Urban MVS Meshes

    Lingjie Zhu (CASIA), Shuhan Shen (Chinese Academy of Sciences), Zhanyi Hu (Chinese Academy of Sciences)

  • High Dimensional Space Model for Dense Monocular Surface Recovery

    Vladislav Golyanik (DFKI), Didier Stricker (DFKI)

  • Fast and Efficient Depth Map Estimation from Light Fields

    Yuriy Anisimov (DFKI), Didier Stricker (DFKI)

  • Direct Multichannel Tracking

    Carlos A Jaramillo (CUNY Graduate Center), Yuichi Taguchi (MERL), Chen Feng (MERL)

  • Loop-Closure Detection in Urban Scenes for Autonomous Robot Navigation

    Fabiola Maffra (ETH Zurich), Lucas Teixeira (ETH Zurich), Zetao Chen (ETH Zurich), Margarita Chli (ETH Zurich)

  • Fast and Accurate Satellite Multi-view Stereo using Edge-Aware Interpolation

    Ke Wang (UNC Chapel Hill), Jan-Michael Frahm (UNC Chapel Hill)

  • Registration of 3D Point Clouds using Mean Shift Clustering on Rotations and Translations

    Ido Haim Ferencz (Univ. of Haifa), Ilan Shimshoni (Univ. of Haifa)

  • Learning quadrangulated patches for 3D shape parameterization and completion

    Kripasindhu Sarkar (Univ. of Kaiserslautern), Kiran Varanasi (German Research Center for AI), Didier Stricker (DFKI)

  • Symmetry-aware Facade Parsing with Occlusions

    Andrea Cohen (ETH Zurich), Martin R. Oswald (ETH Zurich), Yanxi Liu (Penn State University), Marc Pollefeys (ETH Zurich)

  • Unsupervised 3D Shape Induction from 2D Views of Multiple Objects

    Matheus A Gadelha (UMass Amherst), Subhransu Maji (UMass Amherst), Rui Wang (UMass Amherst)

  • Hierarchical Surface Prediction for 3D Object Reconstruction

    Christian Haene (UC Berkeley), Shubham Tulsiani (UC Berkeley), Jitendra Malik (UC Berkeley)

  • Towards Accurate Markerless Human Shape and Pose Estimation over Time

    Yinghao Huang (Max Planck Institute), Federica Bogo (Microsoft), Christoph Lassner (Univ. of Tubingen), Angjoo Kanazawa (Univ. of Maryland), Peter Gehler (Max Planck Institute), Javier Romero (Body Labs Inc.), Ijaz Akhter (ANU), Michael Black (Max Planck Institute)

  • 3D Object Discovery and Modeling Using Single RGB-D Images Containing Multiple Object Instances

    Wim Abbeloos (KU Leuven), Esra Cansizoglu (MERL), Sergio S Caccamo (KTH Royal Institute of Technology), Yuichi Taguchi (MERL), Yakiyasu Domae (MERL)

  • Reconstructing 3D Human Poses from Keyword Based Image Database Query

    Mo'taz A. Al-Hami (Hashemite University), Rolf Lakaemper (Temple University)


Oral Session 5

Session Chair: Guy Godin

  • Learning Human Motion Models for Long-term Predictions

    Partha Ghosh (ETH Zurich), Jie Song (ETH Zurich), Emre Aksan (ETH Zurich), Otmar Hilliges (ETH Zurich)

  • Real-time Full-Body Motion Capture from Video and IMUs

    Charles Malleson (Univ. of Surrey), Marco Volino(Univ. of Surrey), Andrew Gilbert (Univ. of Surrey), Matthew Trumble (Univ. of Surrey), John Collomosse (Univ. of Surrey), Adrian Hilton (Univ. of Surrey)


Spotlight Session 4

Session Chair: Guy Godin

  • Performance Evaluation of 3D Correspondence Grouping Algorithms

    Jiaqi Yang (Huazhong University of Science and Technology), Ke Xian (Huazhong University of Science and Technology), Yang Xiao (Huazhong University of Science and Technology), Zhiguo Cao (Huazhong University of Science and Technology)

  • Spatial maps: from low rank spectral to sparse spatial functional representations

    Andrea Gasparetto (Univ. Ca' Foscari of Venice), Luca Cosmo (Univ. of Venice), Emanuele Rodolà (Sapienza University of Rome), Michael Bronstein (Univ. della Svizerra Italiana), Andrea Torsello (Univ. Ca' Foscari of Venice)

  • Efficient Model-free Anthropometry from Depth Data

    Thomas Probst (ETH Zurich), Andrea Fossati (ETH Zurich), Mathieu Salzmann (EPFL), Luc Van Gool (ETH Zurich)

  • Robust 3D Human Motion Reconstruction Via Dynamic Template Construction

    Zhong Li (Univ. of Delaware), Yu Ji (Plex-VR), Wei Yang (Univ. of Delaware), Yang Yang (Univ. of Delaware), Jinwei Ye (Louisiana State University), Jingyi Yu (Univ. of Delaware)


Oral Session 6

Session Chair: Dani Lischinski

  • Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision

    Dushyant Mehta (MPI Informatik), Helge Rhodin (EPFL), Dan Casas (Univ. Rey Juan Carlos), Pascal Fua (EPFL), Oleksandr Sotnychenko (MPI Informatik), Weipeng Xu (MPI Informatik), Christian Theobalt (MPI Informatik)

  • Efficient Deformable Shape Correspondence via Kernel Matching

    Matthias Vestner (TU Munich), Zorah Laehner (TU Munich), Amit Boyarski (Technion), Or Litany (TAU), Ron Slossberg (Technion), Tal Remez (TAU), Emanuele Rodolà (Sapienza University of Rome), Alex Bronstein (Technion), Michael Bronstein (Univ. della Svizerra Italiana), Ron Kimmel (Technion), Daniel Cremers (TU Munich)


Spotlight Session 5

Session Chair: Dani Lischinski

  • Using learning of speed to stabilize scale in monocular localization and mapping

    Duncan P Frost (Univ. of Oxford), Victor Prisacariu (Univ. of Oxford), David Murray (Univ. of Oxford)

  • SEGCloud: 3D Semantic Segmentation on Point Cloud

    Lyne P Tchapmi (Stanford University), Christopher Choy (Stanford University), Iro Armeni (Stanford University), Silvio Savarese (Stanford University)

  • Fast Multiview 3D Scan Registration using Planar Structures

    Uttaran Bhattacharya (Indian Institute of Science), Sumit Veerawal (Indian Institute of Science), Venu Govindu (Indian Institute of Science)

  • Simultaneous Hand Pose and Skeleton Bone-Lengths Estimation from a Single Depth Image

    Jameel Malik (DFKI), Ahmed Elhayek (DFKI), Didier Stricker (DFKI)

  • 3D Object Classification via Spherical Projections

    Zhangjie Cao (Tsinghua University), Qixing Huang (UT Austin), Kartik Ramani (Purdue University)

  • Metric Monocular Depth from Small Motion Accelerated

    Christopher Ham (University of Queensland), MingFang Chang (CMU), Simon Lucey (CMU), Surya Singh (University of Queensland)


Poster Session 3

  • Line Association and Vanishing Point Estimation with Binary Quadratic Programming

    Gim Hee Lee (National University of Singapore)

  • Scene Semantic Reconstruction from Egocentric RGB-D-Thermal Videos

    Rachel Luo (Stanford University), Ozan Sener (Stanford University), Silvio Savarese (Stanford University)

  • Single View Parametric Building Reconstruction from Satellite Imagery

    Ke Wang (UNC Chapel Hill), Jan-Michael Frahm (UNC Chapel Hill)

  • Accurate Calibration of Multiple Pan-Tilt Cameras for Live Broadcasts

    Masanori Kano (Japan Broadcasting Corp.), Hidehiko Okubo (Japan Broadcasting Corp.), Masaki Takahashi (Japan Broadcasting Corp.), Kensuke Ikeya (Japan Broadcasting Corp.), Kensuke Hisatomi (Japan Broadcasting Corp.), Tomoyuki Mishina (Japan Broadcasting Corp.)

  • Complete 3D Room Geometry Reconstruction Using Audio-Visual Sensors

    Hansung Kim (Univ. of Surrey), Luca Remaggi (Univ. of Surrey), Philip JB Jackson (Univ. of Surrey), Fazi Filippo (Univ. of Southampton), Adrian Hilton (Univ. of Surrey)

  • Barcode: Global Binary Patterns for Fast Visual Inference

    Sonali Patil (Purdue University), Teng-Yok Lee (MERL), Srikumar Ramalingam (Univ. of Utah), Yuichi Taguchi (MERL), Bedrich Benes (Purdue University)

  • Cross-modal Attribute Transfer for Rescaling 3D Models

    Lin Shao (Stanford University), Angel X Chang (Princeton University), Manolis Savva (Princeton University), Hao Su (UC San Diego), Leonidas Guibas (Stanford University)

  • Point Cloud Registration With Virtual Interest Points from Implicit Quadric Surface Intersections

    Mirza Tahir Ahmed (Queen's University), Joshua Marshall (Queen's University), Michael Greenspan (Queen's University)

  • Motion Compensation for Phase-Shift Structured-Light Systems Based On a Total-Variation Framework

    Jonathan Boisvert (National Research Council Canada), Marc-Antoine Drouin (National Research Council Canada), Michel Picard (National Research Council Canada), Louis-Guy Dicaire (National Research Council Canada), Guy Godin (National Research Council Canada)

  • Matterport3D: Learning from RGB-D Data in Indoor Environments

    Thomas Funkhouser (Princeton University), Angel Chang (Princeton University), Angela Dai (Stanford University), Maciej Halber (Princeton University), Manolis Savva (Princeton University), Shuran Song (Princeton University), Andy Zheng (Princeton University), Yinda Zhang (Princeton University), Matthias Niessner (TU Munich)

  • Joint 3D Reconstruction of a Static Scene and Moving Objects

    Sergio S Caccamo (KTH Royal Institute of Technology), Esra Cansizoglu (MERL), Yuichi Taguchi (MERL)

  • Fuzzy Correspondences For Robust Shape Registration

    Abhishek Kolagunda (Univ. of Delaware), Scott E Sorensen (Univ. of Delaware), Philip Saponaro (Univ. of Delaware), Wayne Treible (Univ. of Delaware), Chandra Kambhamettu (Univ. of Delaware)