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

Keynote Speakers

Bill Freeman


Jana Kosecka

George Mason University

Steve Seitz

UW/ Google

Marc Pollefeys


Rick Szeliski


Conference Program Overview

Tuesday, 10/25/16
9:00 - 9:15 AM Opening Remarks
9:15 - 10:00 AM Keynote 1: Steve Seitz, "The Holodeck"
10:00 - 10:30 AM Coffee Break
10:30 - 11:30 AM Oral Session 1
11:30 - 2:00 PM Lunch & Poster session 1
2:00 - 2:45 PM Keynote 2: Marc Pollefeys, “Semantic 3D Reconstruction"
2:45 - 3:10 PM Coffee Break
3:10 - 4:10 PM Oral Session 2
5:00 - 8:00 PM Welcome Reception (@Ford Gardens, Conference Center)

Wednesday, 10/26/16
9:00 - 9:15 AM Announcements
9:15 - 10:00 AM Keynote 3: Rick Szeliski, “3D Reconstruction for Image-Based Rendering"
10:00 - 10:30 AM Coffee Break
10:30 - 11:30 AM Oral Session 3
11:30 - 2:00 PM Lunch & Poster session 2
2:00 - 2:45 PM Keynote 4: Stefano Soatto, “Object Detection in the Deep Scene"
2:45 - 3:10 PM Coffee Break
3:10 - 4:10 PM Oral Session 4
4:30 - 6:00 PM Tour of Stanford Campus
6:00 - 8:00 PM Banquet

Thursday, 10/27/16
9:00 - 9:15 AM Announcements
9:15 - 10:00 AM Keynote 5: Jana Kosecka, “Semantic Understanding for Robot Perception"
10:00 - 10:30 AM Coffee Break
10:30 - 11:30 AM Oral Session 5
11:30 AM - 2:00 PM Lunch & Poster session 3
2:00 - 2:45 PM Keynote 6: Bill Freeman, “Learning about the World by Hitting Things with a Drumstick"
2:45 - 3:10 PM Coffee Break
3:10 - 3:50 PM Oral Session 6
3:50 - 4:30 PM Awards, Closing Remarks and 3DV-17

Conference Program Details

Oral Session 1

Session Chair: Richard Newcombe

  • Matching Deformable Objects in Clutter

    Luca Cosmo (University of Venice), Emanuele Rodola* (USI Lugano, Switzerland)*, Jonathan Masci, Andrea Torsello (University of Venice), Michael Bronstein

  • Progressive 3D Modeling All the Way

    Alex Locher* (ETH Zürich)*, Michal Havlena (ETH Zurich), Luc Van Gool (ETH Zurich)

  • SceneNN: a Scene Meshes Dataset with aNNotations

    Binh-Son Hua* (SUTD)*, Quang-Hieu Pham (SUTD), Duc Thanh Nguyen, Minh-Khoi Tran, Lap-Fai Yu, Sai-Kit Yeung (Singapore University of Technology and Design)

Oral Session 2

Session Chair: Matthias Niessner

  • A Hybrid Structure/Trajectory Constraint for Visual SLAM

    Angelique Loesch* (CEA LIST)*, Steve Bourgeois (CEA LIST), Vincent Gay-Bellile (CEA LIST), Michel Dhome (Blaise Pascal University)

  • Real-time surface of revolution reconstruction on dense SLAM

    Liming YANG* (Ecole Centrale de Nantes)*, Hideaki Uchiyama, Jean-Marie Normand, Guillaume Moreau, Hajime Nagahara, Rin-ichiro Taniguchi

  • Monocular, Real-Time Surface Reconstruction using Dynamic Level of Detail

    Jacek Zienkiewicz* (Imperial College London)*, Chourmouzios Tsiotsios (Imperial College London), Andrew Davison (Imperial College London), Stefan Leutenegger (Imperial College London)

Poster Session 1

  1. A Large-Scale 3D Object Recognition dataset

    Thomas Sølund* (Danish Technological Institute)*, Anders Buch (University of Southern Denmark), Norbert Krüger (University of Southern Denmark), Henrik Aanæs (Technical University of Denmark)

  2. Robust Feature-Preserving Denoising of 3D Point Clouds


  3. Registration of Point Clouds Based on the Ratio of Bidirectional Distances

    Jihua Zhu* (Xi'an Jiaotong University)*, Di Wang (Xi'an Jiaotong University), Xiuxiu Bai (Xi'an Jiaotong University), Huimin Lu, Congcong Jin (Xi'an Jiaotong University), Zhongyu Li (University of North Carolina at Charlotte)

  4. Point Cloud Noise and Outlier Removal for Image-Based 3D Reconstruction

    Katja Wolff (ETH Zurich), Changil Kim* (ETH Zurich)*, Henning Zimmer (Disney Research), Christopher Schroers (Disney Research), Mario Botsch (Bielefeld University), Olga Sorkine-Hornung (ETH Zurich), Alexander Sorkine-Hornung (Disney Research Zurich)

  5. Exemplar-Based 3D Shape Segmentation in Point Clouds

    Rongqi Qiu* (University of Southern California)*, Ulrich Neumann (University of Southern California)

  6. 3D Data Acquisition and Registration using Two Opposing Kinects

    Vahid Soleimani* (University of Bristol)*, Majid Mirmehdi (University of Bristol), Dima Damen (University of Bristol), Sion Hannuna (University of Bristol), Massimo Camplani (University of Bristol)

  7. Robust Recovery of Heavily Degraded Depth Measurements

    Gilad Drozdov* (Technion)*, Guy Gilboa (Technion), yevgeny shapiro (Technion)

  8. Multi-body Non-rigid Structure-from-Motion

    Suryansh Kumar (ANU), yuchao Dai* (ANU)*, Hongdong Li (Australian National University)

  9. Large Scale SfM with the Distributed Camera Model

    Chris Sweeney* (University of Washington)*, Victor Fragoso (West Virginia Univeristy), Tobias Hollerer (University of California Santa Barbara), Matthew Turk (University of California Santa Barbara)

  10. Optical Flow for Rigid Multi-Motion Scenes

    Tomas Gerlich* (U of Illinois at Chicago)*, Jakob Eriksson (U of Illinois at Chicago)

  11. Absolute pose and structure from motion for surfaces of revolution: minimal problems using apparant contours

    Cody Phillips* (University Of Pennsylvania)*, Kostas Daniilidis (University of Pennsylvania)

  12. Deep Stereo Fusion: combining multiple disparity hypotheses with deep-learning

    Matteo Poggi* (University of Bologna)*, Stefano Mattoccia (University of Bologna)

  13. Fast Obstacle Detection using Sparse Edge-based Disparity Maps

    Dexmont Pena Carrillo* (Dublin City University)*, Alistair Sutherland (Dublin City University)

  14. A Depth Restoration Occlusionless Temporal Dataset

    Daniel Rotman* (Technion)*, Guy Gilboa (Technion)

  15. Proceduralization for Editing 3D Architectural Models

    Ilke Demir* (Purdue University)*, Daniel Aliaga (Purdue University), Bedrich Benes (Purdue University)

  16. Model-based Outdoor Performance Capture

    Nadia Robertini (MPI Informatiks), Dan Casas* (MPI for Informatiks)*, Helge Rhodin (MPI Informatiks), Hans-Peter Seidel (MPI Informatiks), Christian Theobalt (MPI Informatiks)

  17. Rapid Hand Shape Reconstruction with Chebyshev Phase Shifting

    Daniel Moreno* (Brown University)*, WOOKYEON HWANG (BROWN UNIVERSITY), Gabriel Taubin (Brown University)

  18. Computing temporal alignments of human motion sequences in wide clothing using geodesic patches

    Aurela Shehu* (Inria Grenoble Rhône-Alpes)*, Jinlong YANG (INRIA), jean-sebastien Franco (inria), Franck Hetroy-Wheeler (Grenoble INP / Inria), Stefanie Wuhrer (Inria)

  19. HS-Nets : Estimating Human Body Shape from Silhouettes with Convolutional Neural Networks

    Endri Dibra* (ETH Zurich)*, Himanshu Jain (ETH Zurich), Cengiz Oztireli (ETH Zurich), Remo Ziegler (Vizrt AG), Markus Gross (ETH Zurich, Disneyresearch Zurich)

  20. Energy-based Global Ternary Image for Action Recognition Using Sole Depth Sequences

    Mengyuan Liu* (Peking University)*, Hong Liu (Peking University), Chen Chen (University of Central Florida)

Welcome Reception

The Welcome Reception will take place on Tuesday October 25th, from 5.00-8.00PM. It will be hosted in the Ford Gardens at the Francis C. Arrillaga Alumni Center (same location as poster session).

Oral Session 3

Session Chair: Emanuele Rodolà

  • Deeper Depth Prediction with Fully Convolutional Residual Networks

    Iro Laina* (Technische Universität München)*, Christian Rupprecht (Technische Universität München), Vasileios Belagiannis (University of Oxford), Federico Tombari (Univ. Bologna, TU Munich), Nassir Navab

  • Depth from Gradients in Dense Light Fields for Object Reconstruction

    Kaan Yucer* (ETH Zurich)*, Changil Kim (ETH Zurich), Alexander Sorkine-Hornung (Disney Research Zurich), Olga Sorkine-Hornung (ETH Zurich)

  • Single-image RGB Photometric Stereo With Spatially-varying Albedo

    Ayan Chakrabarti* (TTI-Chicago)*, Kalyan Sunkavalli (Adobe Research)

Oral Session 4

Session Chair: Sudipta Sinha

  • 3D Saliency for Finding Landmark Buildings

    Nikolay Kobyshev* (ETH Zurich)*, Hayko Riemenschneider (Computer Vision Lab), Andras Bodis-Szomoru (ETH Zurich), Luc Van Gool (ETH Zurich)

  • Dense wide-baseline scene flow from two handheld video cameras

    Christian Richardt* (Intel VCI)*, Hyeongwoo Kim (MPII), Levi Valgaerts, Christian Theobalt (MPI Informatiks)

  • Automatic 3D Model Alignment for Mixed Image-Based Rendering

    Rodrigo Ortiz Cayon, Abdelaziz Djelouah* (Inria)*, francisco Vitor Suzano Massa, Mathieu Aubry (ENPC), George Drettakis (INRIA)

Poster Session 2

  1. HDRFusion: HDR SLAM using a low-cost auto-exposure RGB-D sensor

    Shuda Li* (University of Bristol)*, Ankur Handa (Imperial College London), Yang Zang (Univ of Bristol), Andrew Calway (University of Bristol)

  2. Single View 3D Reconstruction under an Uncalibrated Camera and an Unknown Mirror Sphere

    Kai Han* (The University of Hong Kong)*, Kwan-Yee Wong (University of Hong Kong), Xiao Tan

  3. Tracking deformable surfaces that undergo topological changes using an RGB-D camera

    Aggeliki Tsoli* (FORTH Greece)*, Antonis Argyros (ICS FORTH & Computer Science Department, University of Crete, Heraklion, Greece)

  4. Video Depth-From-Defocus

    Hyeongwoo Kim* (MPII)*, Christian Richardt (Intel VCI), Christian Theobalt (MPI Informatiks)

  5. Robust Tracking in Low Light and Sudden Illumination Changes

    Hatem Alismail* (Carnegie Mellon University)*, Brett Browning, Simon Lucey

  6. Real-time Halfway Domain Reconstruction of Motion and Geometry

    Lucas Thies* (FAU)*, Michael Zollhoefer (Max Planck Institute for Informatics), Christian Richardt (Intel VCI), Christian Theobalt (MPI Informatiks), Marc Stamminger

  7. 3D Face Reconstruction by Learning from Synthetic Data

    Elad Richardson* (Technion)*, Matan Sela (Technion), Ron Kimmel (Technion - Israel Institute of Technology)

  8. Structure from Category: A Generic and Prior-less Approach

    Chen Kong* (Carnegie Mellon University)*, Rui Zhu (Carnegie Mellon University), Hamed Kiani Galoogahi (CMU), Simon Lucey

  9. Radiometric Scene Decomposition: Scene Reflectance, Illumination, and Geometry from RGB-D Images

    Ko Nishino* (Drexel University)*, Stephen Lombardi (Oculus)

  10. CNN-based Object Segmentation in Urban LIDAR With Missing Points

    Allan Zelener* (CUNY Graduate Center)*, Ioannis Stamos (City University of New York)

  11. Multiview RGB-D Dataset for Object Instance Detection

    Georgios Georgakis* (George Mason University)*, Md Reza (George Mason University), Arsalan Mousavian (George Mason University), Phi Hung Le (George Mason University), Jana Kosecka (George Mason University)

  12. Robust Real-Time 3D Face Tracking from RGBD Videos under Extreme Pose, Depth, and Expression Variations

    Hai Pham* (Rutgers University)*, Vladimir Pavlovic (Rutgers University)

  13. A Single-shot Multi-path Interference Resolution for Mirror-based Full 3D Shape Measurement with a Correlation-based ToF Camera

    Shohei Nobuhara* (Kyoto University)*, Takashi Kashino (Kyoto University), Takashi Matsuyama (Kyoto University), Kouta Takeuchi (NTT Laboratories), Kensaku Fujii (NTT)

  14. Cotemporal Multi-View Video Segmentation

    Abdelaziz Djelouah* (Inria)*, jean-sebastien Franco (inria), Edmond Boyer (inria), Patrick Perez (Technicolor), George Drettakis (INRIA)

  15. Multi-View Inpainting for Image-Based Scene Editing and Rendering

    Theo Thonat* (INRIA)*, Eli Shechtman (Adobe), Sylvain Paris (Adobe), George Drettakis (INRIA)

  16. Learning to Navigate the Energy Landscape

    Julien Valentin, Angela Dai* (Stanford University)*, Matthias Niessner ("Stanford University, USA"), Pushmeet Kohli, Philip Torr (University of Oxford), Shahram Izadi, Cem Keskin

  17. A Closed-form Bayesian Fusion Equation using Occupancy Probabilities

    Charles Loop* (Microsoft Research)*, Qin Cai (Microsoft Research), Sergio Orts-Escolano, Philip Chou

  18. Consistent Discretization and Minimization of the L1 Norm on Manifolds

    Yoni Choukroun* (Technion)*, Matan Sela (Technion), Ron Kimmel (Technion - Israel Institute of Technology), Alex Bronstein (Technion, Israel institute o ftechnology)

  19. Coupled Functional Maps

    Davide Eynard* (Università della Svizzera Ital)*, Klaus Glashoff (Università della Svizzera Italiana), Emanuele Rodola (USI Lugano, Switzerland), Michael Bronstein

Oral Session 5

Session Chair: Bryan Russell

  • Shape Analysis with Anisotropic Windowed Fourier Transform

    Simone Melzi* (University of Verona)*, Emanuele Rodola (USI Lugano, Switzerland), Umberto Castellani (University of Verona), Michael Bronstein

  • Synthesizing Training Images for Boosting Human 3D Pose Estimation

    Wenzheng Chen* (Shandong University)*, Yangyan Li, Hao Su, Zhenhua Wang, Dani Lischinski, Changhe Tu, Daniel CohenOr, Baoquan Chen

  • Face Reconstruction on Mobile Devices Using a Height Map Shape Model and Fast Regularization

    Fabio Maninchedda* (ETH Zurich)*, Christian Häne (UC Berkeley), Martin Oswald (ETH Zurich), Marc Pollefeys (ETHZurich)

Oral Session 6

Session Chair: Noah Snavely

  • SpectroMeter: Amortized Sublinear Spectral Approximation of Distance on Graphs

    Roee Litman* (Tel-Aviv University)*, Alex Bronstein (Technion, Israel institute o ftechnology)

  • Learning a general-purpose confidence measure based on O(1) features and a smarter aggregation strategy for semi global matching

    Matteo Poggi* (University of Bologna)*, Stefano Mattoccia (University of Bologna)

Poster Session 3

  1. Room Layout Estimation with Object and Material Attributes Information using a Spherical Camera

    Hansung Kim* (University of Surrey)*, Teo Campos (University of Surrey), Adrian Hilton (University of Surrey)

  2. Regularized 3D Modeling From Noisy Building Reconstructions

    Thomas Holzmann* (Graz University of Technology)*, Friedrich Fraundorfer (Graz University of Technology), Horst Bischof (Graz University of Technology)

  3. Detecting and Correcting Shadows in Urban Point Clouds and Image Collections

    Maximilien Guislain* (Université Lyon 1)*, Julie Digne (CNRS), Raphaëlle Chaine (LIRIS Université Lyon 1), Dimitri Kudelski (Technodigit), Pascal Lefebvre-Albaret (Technodigit)

  4. X-Tag: A Fiducial Tag for Flexible and Accurate Bundle Adjustment

    Tolga Birdal* (Technical University of Munich)*, ievgeniia Dobryden (Technical University of Munich), Slobodan Ilic (Siemens AG)

  5. Will it last? Learning Stable Features for Long-Term Visual Localization

    Marcin Dymczyk* (ETH Zurich)*, Elena Stumm (ETH Zurich), Juan Nieto (ETH Zurich), Roland Siegwart (ETH Zurich), Igor Gilitschenski (ETH Zurich)

  6. A 3D Reconstruction with High Density and Accuracy using Laser Profiler and Camera Fusion System on a Rover

    Ryoichi Ishikawa* (The University of Tokyo)*, Roxas Menandro (The University of Tokyo), Yoshihiro Sato (The University of Tokyo), Takeshi Oishi (The Univ. of Tokyo), Takeshi Masuda, Katsushi Ikeuchi (Microsoft Research Asia)

  7. Quaternionic Upsampling: Hyperspherical Techniques for 6 DoF Pose Tracking

    Benjamin Busam* (Technical University of Munich)*, Marco Esposito, Benjamin Frisch, Nassir Navab

  8. Camera Motion from Group Synchronization

    Federica Arrigoni* (University of Udine)*, Andrea Fusiello (Udine University), Beatrice Rossi (STMicroelectronics)

  9. Discriminative Filters for Depth from Defocus

    Fahim Mannan* (McGill University)*, Michael Langer (McGill University)

  10. Robust Plane-based Calibration of Multiple Non-Overlapping Cameras

    Chen Zhu* (ShanghaiTech University)*, Zihan Zhou, Ziran Xing, Yanbing Dong, Yi Ma, Jingyi Yu

  11. Single-shot Time-of-Flight Phase Unwrapping Using Two Modulation Frequencies

    Changpeng Ti* (Univertiys of Kentucky)*, Ruigang Yang (University of Kentucky), James Davis (University of California, Santa Cruz)

  12. Fast Single Shot Detection and Pose Estimation

    Patrick Poirson* (UNC Chapel Hill)*, Philip Ammirato (UNC Chapel Hill), Cheng-Yang Fu (UNC Chapel Hill), Wei Liu (UNC Chapel Hill), Jana Kosecka ("George Mason University, USA"), Alex Berg (UNC Chapel Hill)

  13. Learning camera viewpoint using CNN to improve 3D body pose estimation

    Mona Fathollahi Ghezelghieh* (University of South Florida)*, Rangachar Kasturi (University of South Florida), Sudeep Sarkar (University of South Florida)

  14. 3D Human Pose Estimation via Deep Learning from 2D annotations

    Ernesto Brau* (Boston College)*, Hao Jiang (Boston College)

  15. Synthetic prior design for real-time face tracking

    Steven McDonagh* (Disney Research)*, Martin Klaudiny (Disney Research), Derek Bradley (Disney Research), Thabo Beeler (Disney Research), Kenny Mitchell (Disney Research), Iain Matthews (Disney Research Pittsburgh)

  16. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

    Fausto Milletari* (Technical University Munich)*, Nassir Navab, Seyed-Ahmad Ahmadi (Ludwig Maximilian Universität)

  17. Multi-Label Semantic 3D Reconstruction using Voxel Blocks

    Ian Cherabier* (ETH Zurich)*, Christian Häne (UC Berkeley), Martin Oswald (ETH Zurich), Marc Pollefeys (ETHZurich)

  18. Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks

    Arsalan Mousavian* (George Mason University)*, Hamed Pirsiavash (University of Maryland Baltimore County), Jana Kosecka (George Mason University)

  19. Comparison of Radial and Tangential Geometries for Cylindrical Panorama

    Faezeh Amjadi (Montreal University), sebastien Roy* (Montreal University)*

  20. Tutorials and Exhibits

    Friday, 10/28/16

    9:00 - 12:00 AM Tutorial 1: Semantic and Structured 3D Modeling Tutorial 2: Understanding 3D and Visuo-Motor Learning
    12:00 - 2:00 PM Lunch
    2:00 - 5:00 PM Tutorial 3: 3D Object Geometry from Single Image Tutorial 4: Large-­scale 3D Modeling from Crowdsourced Data
    Exhibits & Demos
    10:00 AM - 5:00 PM Exhibits & Demos
    *See below for the full list of Exhibitors and Demos.