Monday 19 | Tuesday 20 | Wednesday 21 | Thursday 22 | |
09.00-09.10 | Announcements | Opening Remarks | Announcements | Announcements |
09.10-10.10 | Tutorial 1 | Keynote 1 | Keynote 2 | Keynote 3 |
10.15-10.40 | Coffee Break | Coffee Break | Coffee Break | |
10.40-12.00 | Oral Session 1 | Oral Session 3 | Oral Session 5 | |
12.00-14.00 | Lunch | Lunch | Lunch | Lunch |
14.00-15.20 | Tutorial 2 | Oral Session 2 | Oral Session 4 | Oral Session 6 |
15.20-16.00 | Coffee Break | Coffee Break | Coffee Break | |
16.00-18.00 | Poster Session 1 | Poster Session 2 | Poster Session 3 | |
Welcome Reception | Banquet | Awards & Closing |
Day 1, Monday October 19
Tutorial 1, 09.00 – 12.00, Amphitheatre Mérieux
Tutorial 2, 14.00 – 17.00, Amphitheatre Mérieux
Day 2, Tuesday October 20
Keynote 1, 09.10 – 10.10, Amphitheatre Mérieux
Alexander Sorkine-Hornung, Disney Research Zurich |
Title: Production-oriented research on Imaging and Video
Abstract: Computer vision research for movies and theme park productions at Disney poses unique challenges in terms of reliability and performance of the algorithms and quality of results.For instance, many existing strategies for image-based 3D reconstruction or video processing have been carefully designed towards sparsely sampled, heterogeneous image data. Such techniques (involving, e.g., complex global optimization) usually become fundamentally impractical to apply to content captured with a dense array of modern cinema cameras at 120 fps at 4k resolution and beyond. At the same time, these methods ignore novel challenges and opportunities arising from extremely dense input. In this talk, I will present our ongoing work in the Imaging and Video Group at Disney Research on 3D scene modeling and processing from densely sampled videos and light fields, which breaks with a number of established practices in computer vision in order to achieve result quality and speed unparalleled by existing methods. Bio: Alexander Sorkine-Hornung is Senior Research Scientist at Disney Research Zurich, heading the Imaging and Video group. Before joining Disney, Alexander was a postdoctoral researcher at the Computer Graphics Laboratory at ETH Zurich. He obtained his PhD in Computer Science at RWTH Aachen in 2008. Alexander’s research interests lie in all areas related to digital image and video processing. A representative list of topics includes light field and video processing, big data imaging, image-based 3D reconstruction and rendering, color processing, stereoscopy, and visual saliency analysis. Furthermore, he is interested in innovative applications of image-based technologies in the fields of 2D animation and interactive environments. In 2012 Alexander received the Eurographics Young Researcher Award. The research and technologies developed by his group already had significant impact on various Disney park attractions and movie productions, with film credits on movies such as Maleficent, Cinderella, and Big Hero 6. |
Oral Session 1, 10.40 – 12.00, Amphitheatre Mérieux
Chair: Michael Goesele, TU Darmstadt |
Depth Fields: Extending Light Field Techniques to Time-of-Flight Imaging Suren Jayasuriya, Adithya Pediredla, Sriram Sivaramakrishnan, Alyosha Molnar, Ashok Veeraraghavan |
Towards Probabilistic Volumetric Reconstruction using Ray Potentials Ali Ulusoy, Andreas Geiger, Michael Black |
Multi-view Reconstruction of Highly Specular Surfaces in Uncontrolled Environments Clément Godard, Peter Hedman, Wenbin Li, Gabriel Brostow |
x-hour Outdoor Photometric Stereo Yannick Hold-Geoffroy, Jinsong Zhang, Paulo F. U. Gotardo, Jean-Francois Lalonde |
Oral Session 2, 14.00 – 15.20, Amphitheatre Mérieux
Chair: Philippos Mordohai, Stevens Institute of Technology |
Automatic Recovery of Networks of Thin Structures Meng Song, Daniel Huber |
Global Mesh Denoising with Fairness Sk. Mohammadul Haque, Venu Madhav Govindu |
Graph Edit Distance based on Triangle-Stars Decomposition for Deformable 3D Objects Recognition Kamel Madi, Eric Paquet, Hamida Seba, Hamamache Kheddouci |
Motion Cooperation: Smooth Piece-Wise Rigid Scene Flow from RGB-D Images Mariano Jaimez Tarifa, Mohamed Souiai, Jörg Stückler, Javier Gonzalez-Jimenez, Daniel Cremers |
Poster Session 1, 16.00-18.00, Exposition Hall
Orals from Session 1 and 2 are requested to present posters as well
Title and authors |
1. Ensemble Classifier for Combining Stereo Matching Algorithms Aristotle Spyropoulos, Philippos Mordohai |
2. RGB-D Visual Search with Compact Binary Codes Alioscia Petrelli, Danilo Pau, Emanuele Plebani, Luigi Di Stefano |
3. Establishing a Probabilistic Depth Map from Focused Plenoptic Cameras Niclas Zeller, Franz Quint, Uwe Stilla, |
4. A 3D Scene Analysis Framework and Descriptors for Risk Evaluation Rob Dupre, Vasilis Argyriou, Georgios Tzimiropoulos, Darrel Greenhill |
5. Segmentation of 3D Lidar points using Extruded Surface of Cross Section Hitoshi Niigaki, Jun Shimamura, Akira Kojima |
6. A Multi-View Structured Light System for Highly Accurate 3D Modeling Hyowon Ha, Tae-Hyun Oh, In So Kweon |
7.Dense Depth and Albedo from a Single-shot Structured Light Hyowon Ha, Jaesik Park, In So Kweon |
8. Convolutional Fisher Kernels for RGB-D Object Recognition Yanhua Cheng, Rui Cai, Xin Zhao, Kaiqi Huang |
9. Consistent 3D Background Model Estimation from Multi-Viewpoint Videos Iraklis Tsekourakis, Philippos Mordohai |
10. Interference-free Epipole-centered Structured Light Pattern for Mirror-based Multi-view Active Stereo Tomu Tahara, Ryo Kawahara, Shohei Nobuhara, Takashi Matsuyama |
11. Continuous Symmetric Stereo with Adaptive Outlier Handling Chen Li, Lap-Fai Yu, Zhichao Lu, Yasuyuki Matsushita, Kun Zhou, Stephen Lin |
12. Fast and Robust Multi-View 3D Object Recognition in Point Clouds Guan Pang, Ulrich Neumann |
13. Confidence Estimation for Superpixel-based Stereo Matching Rafael Guveia, Aristotle Spyropoulos, Philippos Mordohai |
14. Accurate and Practical 3D Measurement for Translucent Objects by Dashed Lines and Complementary Gray Code Projection Toshihiro Kobayashi, Tomoaki Higo, Masayoshi Yamasaki, Kiwamu Kobayashi, Akihiro Katayama |
15. Low-Cost Depth and Radiological Sensor Fusion to Detect Moving Sources Phillip Riley, Andreas Enqvist, Sanjeev Koppal |
16. Domain adaptation for structure recognition in different building styles Zhizhong Li, Daniel Huber |
17. Half-Occluded Regions and Detection of Pseudoscopy Jonathan Bouchard, Yasin Nazzar, James Clark |
18. Depth Fields: Extending Light Field Techniques to Time-of-Flight Imaging Suren Jayasuriya, Adithya Pediredla, Sriram Sivaramakrishnan, Alyosha Molnar, Ashok Veeraghavan |
19. Towards Probabilistic Volumetric Reconstruction using Ray Potentials Ali Ulusoy, Andreas Geiger, Michael Black |
20. Multi-view Reconstruction of Highly Specular Surfaces in Uncontrolled Environments Clément Godard, Peter Hedman, Wenbin Li, Gabriel Brostow |
21. x-hour Outdoor Photometric Stereo Yannick Hold-Geoffroy, Jinsong Zhang, Paulo F. U. Gotardo, Jean-Francois Lalonde |
22. Automatic Recovery of Networks of Thin Structures Meng Song, Daniel Huber |
23. Global Mesh Denoising with Fairness Sk. Mohammadul Haque, Venu Madhav Govindu |
24. Graph Edit Distance based on Triangle-Stars Decomposition for Deformable 3D Objects Recognition Kamel Madi, Eric Paquet, Hamida Seba, Hamamache Kheddouci |
25. Motion Cooperation: Smooth Piece-Wise Rigid Scene Flow from RGB-D Images Mariano Jaimez Tarifa, Mohamed Souiai, Jörg Stückler, Daniel Cremers, Javier Gonzalez-Jimenez |
26. Census-Based Cost on Gradients for Matching under Illumination Differences Christos Stentoumis, George Karras, Aggelos Amditis |
18.30-21.00 Welcome Reception, Exposition Hall
Day 3, Wednesday October 21
Keynote 2, 09.10 – 10.10, Amphitheatre Mérieux
Luc Robert, Autodesk |
Title: 3D Vision at Autodesk
Abstract: Through examples such as 123d® Catch®, Autodesk®Recap® or Memento®, we will show how 3D vision has surfaced on different markets and in different products at Autodesk, and has become a reality for many users. Through the lens of concrete applications and use cases, we will take a look at the current status and upcoming challenges for 3D vision. Bio: Luc Robert obtained his PhD in 1993 from Inria/Ecole Polytechnique. After a 1-year post-doc at Carnegie Mellon University, he joined Inria in 1995 as a Research Scientist. In 1998, he started the REALVIZ company, acquired by Autodesk in 2008. He is now Senior Software Architect for the Reality Solutions department at Autodesk, that develops technologies and products related to photogrammetry and 3D scanning. |
Oral Session 3,10.40 – 12.00, Amphitheatre Mérieux
Chair: Ioannis Stamos, City University of New York |
Efficient Large-Scale Point Cloud Registration Using Loop Closures Takaaki Shiratori, Jerome Berclaz, Michael Harville, Chintan Shah, Taoyu Li, Yasuyuki Matsushita, Stephen Shiller |
MLMD: Maximum Likelihood Mixture Decoupling for Fast and Accurate Point Cloud Registration Benjamin Eckart, Kihwan Kim, Alejandro Troccoli, Alonzo Kelly, Jan Kautz |
Procrustean point-line registration and the NPnP problem Andrea Fusiello, Fabio Crosilla, Francesco Malapelle |
Accurate Isosurface Interpolation with Hermite Data Simon Fuhrmann, Michael Kazhdan, Michael Goesele |
Oral Session 4, 14.00 – 15.20, Amphitheatre Mérieux
Chair: Jean Sebastien Franco, INRIA Grenoble |
3D surface reconstruction from point-and-line cloud Takayuki Sugiura, Akihiko Torii, Masatoshi Okutomi |
Learning Hierarchical Semantic Segmentations of LIDAR Data David Dohan, Brian Matejek, Thomas Funkhouser |
Segmentation based features for wide-baseline multi-view reconstruction Armin Mustafa, Hansung Kim, Evren Imre, Adrian Hilton |
3D Modeling on the Go: Interactive 3D Reconstruction of Large-Scale Scenes on Mobile Devices Thomas Schöps, Torsten Sattler, Christian Häne, Marc Pollefeys |
Poster Session 2, 16.00 -18.00,Exposition Hall
Orals from Session 3 and 4 are requested to present posters as well
Title and authors |
1. On Computing the Translations Norm in the Epipolar Graph Federica Arrigoni, Andrea Fusiello, Beatrice Rossi |
2. Multi-Label Object Categorization Using Histograms of Global Relations Wail Mustafa, Hanchen Xiong, Dirk Kraft, Sandor Szedmak, Justus Piater, Norbert Krüger |
3. LiveScan3D: A Fast and Inexpensive 3D Data Acquisition System for Multiple Kinect v2 Sensors Marek Kowalski, Jacek Naruniec, Michael Daniluk |
4. Optimal Camera Parameters for Depth from Defocus Fahim Mannan, Michael Langer |
5. Light-Field Microscopy with a Consumer Light-Field Camera Loïs Mignard-Debise, Ivo Ihrke |
6. Non-Parametric Spectral Model for Shape Retrieval Andrea Gasparetto, Giorgia Minello, Andrea Torsello |
7. Matchability Prediction for Full-Search Template Matching Algorithms Adrian Penate-Sanchez, Lorenzo Porzi, Francesc Moreno-Noguer |
8. Automatic Indoor 3D Surface Reconstruction with Segmented Building and Object Elements Eric Turner, Avideh Zakhor |
9. Repeatable Local Coordinate Frames for 3D Human Motion Tracking: from Rigid to Non-Rigid Chun-Hao Huang, Federico Tombari, Nassir Navab |
10. Online classification in 3D urban datasets based on hierarchical detection Thomas Flynn, Olympia Hadjiliadis, Ioannis Stamos |
11. Cultural Heritage Acquisition: Geometry-Based Radiometry in the Wild Thomas Hoell, Axel Pinz |
12. Local Hough Transform for 3D Primitive Detection Bertram Drost, Slobodan Ilic |
13. Multiscale Retinex Aggregation to Enable Robust Dense Stereo Correspondence Xiongbiao Luo,A . Jonathan McLeod, Uditha L. Jayarathne, , Terry M. Peters |
14. Accelerated Relative Camera Pose from Oriented Features Steven Mills |
15. Approximate 3D Partial Symmetry Detection Using Co-Occurrence Analysis Chuan Li, Michael Wand, Xiaokun Wu, Hans-Peter Seidel |
16. Synchronization and Self-Calibration for Helmet-Held Consumer Cameras, Applications to Immersive 3D Modeling and 360 Video Maxime Lhuillier,Thanh-Tin Nguyen |
17. 3-d Tessellation of Plant Tissue – A dual optimization approach to cell-level meristem reconstruction from microscopy images Guillaume Cerutti, Sophie Ribes, Carlos Galvan Ampudia, Teva Vernoux, Christophe Godin |
18. Efficient Large-Scale Point Cloud Registration Using Loop Closures Takaaki Shiratori, Jerome Berclaz, Michael Harville, Chintan Shah, Taoyu Li, Yasuyuki Matsushita, Stephen Shiller |
19. FMLMD: Maximum Likelihood Mixture Decoupling for Fast and Accurate Point Cloud Registration Benjamin Eckart, Kihwan Kim, Alejandro Troccoli, Alonzo Kelly, Jan Kautz |
20. Procrustean point-line registration and the NPnP problem Andrea Fusiello, Fabio Crosilla, Francesco Malapelle |
21. Accurate Isosurface Interpolation with Hermite Data Simon Fuhrmann, Michael Kazhdan, Michael Goesele |
22. 3D surface reconstruction from point-and-line cloud Takayuki Sugiura, Akihiko Torii, Masatoshi Okutomi |
23. Learning Hierarchical Semantic Segmentations of LIDAR Data David Dohan, Brian Matejek, Thomas Funkhouser |
24. Segmentation based features for wide-baseline multi-view reconstruction Armin Mustafa, Hansung Kim, Evren Imre, Adrian Hilton |
25. 3D Modeling on the Go: Interactive 3D Reconstruction of Large-Scale Scenes on Mobile Devices Thomas Schöps, Torsten Sattler, Christian Häne, Marc Pollefeys |
26. Planes Detection for Robust Localization and Mapping in RGB-D SLAM systems Hakim El Chaoui El Ghor, David Roussel, Fakhreddine Ababsa, El Houssine Bouyakhf |
20.00-22.00 Conference Banquet, Abbaye de Collonges
Keynote 3, 09.10 – 10.10, Amphitheatre Mérieux
Adrian Hilton, University of Surrey |
Title: 4D Vision for Video-Realistic Interactive Animation
Abstract: Over the past decade advances in computer vision have enabled the 3D reconstruction of dynamic scenes from multiple view video. This has allowed video-based free-viewpoint rendering with the photo-realism of video whilst allowing interactive viewpoint control. This technology initially pioneered for highly controlled indoor scenes has been extended to free-viewpoint rendering of large-scale outdoor scenes such as sports for TV production. Free-viewpoint video content is limited to the replay of the captured performance. This talk will present results of recent research in 4D vision research for actor performance capture which allows both video-realistic free-viewpoint rendering and interactive control of movement. Recent research has introduced methods for spatio-temporal alignment and parametric representation of dynamic shape and appearance from capture performance to allow interactive control whilst maintaining the realism of the captured video. This opens-up the potential for reuse of 4D performance capture to create video-realistic characters for immersive entertainment. This talk will review recent advances and identify future research challenges for 4D vision in entertainment and human motion analysis. Bio: Adrian Hilton, BSc(hons),DPhil,CEng, is Professor of Computer Vision and Graphics and Director of the Centre for Vision, Speech and Signal Processing at the University of Surrey, UK. He leads research investigating the use of computer vision for applications in entertainment content production, visual interaction and clinical analysis. |
Day 4, Thursday October 22
Oral Session 5, 10.40 – 12.00, Amphitheatre Mérieux
Chair: Jean Francois Lalonde, Laval University |
Shadow Detection and Sun Direction in Photo Collections Scott Wehrwein, Kavita Bala, Noah Snavely |
A Bayesian Approach for Selective Image-Based Rendering using Superpixels Rodrigo Ortiz-Cayon, Abdelaziz Djelouah, George Drettakis |
Video based Animation Synthesis with the Essential Graph Adnane Boukhayma, Edmond Boyer |
The Geometry of Colorful, Lenticular Fiducial Markers Ian Schillebeeckx, Joshua Little, Brendan Kelly, Robert Pless |
Oral Session 6, 14.00 – 15.20, Amphitheatre Mérieux
Chair: Adrian Hilton, University of Surrey |
A Combined Generalized and Subject-Specific 3D Head Pose Estimation David Joseph Tan, Federico Tombari, Nassir Navab |
Dictionary Learning based 3D Morphable Model Construction for Face Recognition with Varying Expression and Pose Claudio Ferrari, Giuseppe Lisanti, Stefano Berretti, Alberto Del Bimbo |
Monocular 3D human pose estimation with a semi-supervised graph-based method Mahdieh Abbasi, Hamid Reza Rabiee, Christian Gagné |
Point Pair Features Based Object Detection and Pose Estimation Revisited Tolga Birdal, Slobodan Ilic |
Poster Session 3, 16.00 -17.30,Exposition Hall
Orals from Session 5 and 6 are requested to present posters as well
Title and authors |
1. Super-Resolution Keyframe Fusion for 3D Modeling with High-Quality Textures Robert Maier, Joerg Stueckler, Daniel Cremers |
2. Towards Skeleton based Reconstruction: From Projective Skeletonization to Canal Surface Estimation Bastien Durix, Morin Geraldine, Sylvie Chambon, Celine Roudet, Lionel Garnier |
3. Estimation of Branch Angle from 3D Point Cloud of Plants Lu Lou,Yonghuai Liu, Minglan Shen, Jiwan Han, Fiona Corke, John H. Doonan |
4. Unsupervised Temporal Segmentation of Repetitive Human Actions Based on Kinematic Modeling and Frequency Analysis Qifei Wang, Gregorij Kurillo, Ferda Ofli, Ruzena Bajcsy |
5. On Preserving Structure in Stereo Seam Carving Kuo-Chin Lien, Matthew Turk |
6. Depth Estimation Based on an Infrared Projector and an Infrared Color Stereo Camera by Using Cross-based Dynamic Programming with Cost Volume Filter Kensuke Hisatomi, Masanori Kano, Kensuke Ikeya,Miwa Katayama, Tomoyuki Mishina, Kiyoharu Aizawa |
7. Audio Visual Synchronization of Rhythm Andrew Godbout, Jeffrey Boyd |
8. Super Generalized 4PCS for 3D Registration Mustafa Mohamad, Mirza Tahir Ahmed, David Rappaport, Michael Greenspan |
9. Reconstructing Street-Scenes in Real-Time From a Driving Car Vladyslav Usenko, Jakob Engel, Jörg Stückler, Daniel Cremers |
10. Ground Segmentation based on Loopy Belief Propagation of Sparse 3D Point Clouds Mingfang Zhang, Daniel Morris, Rui Fu |
11. A New Flying Range Sensor: Aerial Scan in Omini-directions Bo Zheng, Xiangqi Huang, Ryoichi Ishikawa, Takeshi Oishi,Katsushi Ikeuchi |
12. Tracking fractures of deformable objects in real-time with an RGB-D sensor Antoine Petit, Vincenzo Lippiello, Bruno Siciliano |
13. Estimating surface normals with depth image gradients for fast and accurate registration Yosuke Nakagawa, Hideaki Uchiyama, Hajime Nagahara, Rin-ichiro Taniguchi |
14. Reconstruction of 3D Pose for Surfaces of Revolution from Range Data Georgios Pavlakos, Kostas Daniilidis |
15. Shadow Detection and Sun Direction in Photo Collections Scott Wehrwein, Kavita Bala, Noah Snavely |
16. A Bayesian Approach for Selective Image-Based Rendering using Superpixels Rodrigo Ortiz-Cayon, Abdelaziz Djelouah, George Drettakis |
17. Video based Animation Synthesis with the Essential Graph Adnane Boukhayma, Edmond Boyer |
18. The Geometry of Colorful, Lenticular Fiducial Markers Ian Schillebeeckx, Joshua Little, Brendan Kelly, Robert Pless, |
19. A Combined Generalized and Subject-Specific 3D Head Pose Estimation David Joseph Tan, Federico Tombari, Nassir Navab |
20. Dictionary Learning based 3D Morphable Model Construction for Face Recognition with Varying Expression and Pose Claudio Ferrari, Giuseppe Lisanti, Stefano Berretti, Alberto Del Bimbo |
21. Monocular 3D human pose estimation with a semi-supervised graph-based method Mahdieh Abbasi, Hamid Reza Rabiee, Christian Gagne |
22. Point Pair Features Based Object Detection and Pose Estimation Revisited Tolga Birdal, Slobodan Ilic |