ETH Zurich - D-INFK - IVC - CVG - Lectures - 3D Vision

3D Vision


Papers

For each project group, we will assign a paper to present, which is chosen in accordance with the group's project. In this way we want to guarantee that a detailed discussion of the paper also is beneficial for your project.

The presentation length will be announced during the semester.

Note: You have access to IEEExplore within the ETH network, i.e. from outside use a VPN client to connect.

March 19

Group 5
“Probabilistic Structure From Motion With Objects (PSfMO)”, Paul Gay; Cosimo Rubino; Vaibhav Bansal; Alessio Del Bue, ICCV 2017
opponent: Group 1

Group 8
“Reconstructing the World in Six Days”, Heinly et al., CVPR 2015
opponent: Group 2

Group 9
“DSAC - Differentiable RANSAC for Camera Localization”, Eric Brachmann, Alexander Krull, Sebastian Nowozin, Jamie Shotton, Frank Michel, Stefan Gumhold, Carsten Rother, CVPR 2017
opponent: Group 3


March 26

Group 10
"Matching neural paths: transfer from recognition to correspondence search", Nikolay Savinov, Lubor Ladicky, Marc Pollefeys
opponent: Group 4

Group 7
“DeMoN: Depth and Motion Network for Learning Monocular Stereo” Benjamin Ummenhofer, Huizhong Zhou, Jonas Uhrig, Nikolaus Mayer, Eddy Ilg, Alexey Dosovitskiy, Thomas Brox, CVPR 2017
opponent: Group 5

Group 17
“End-To-End Learning of Geometry and Context for Deep Stereo Regression”, Alex Kendall; Hayk Martirosyan; Saumitro Dasgupta; Peter Henry; Ryan Kennedy; Abraham Bachrach; Adam Bry, ICCV 2017
opponent: Group 6
Group 14
“Unsupervised Learning of Depth and Ego-Motion From Video”, Tinghui Zhou, Matthew Brown, Noah Snavely, David G. Lowe, CVPR 2017
opponent: Group 8


April 09

Group 1
“Direct Sparse Odometry” (J. Engel, V. Koltun, D. Cremers), In IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018.
opponent: Group 7

Group 2
“Real-Time 3D Reconstruction and 6-DoF Tracking with an Event Camera”, Hanme Kim, Stefan Leutenegger, Andrew Davison, ECCV 2016
opponent: Group 9

Group 3
“CNN-SLAM: Real-Time Dense Monocular SLAM With Learned Depth Prediction”, Keisuke Tateno, Federico Tombari, Iro Laina, Nassir Navab, CVPR 2017
opponent: Group 10
Group 27
"Neural SLAM: Learning to Explore with External Memory", Jingwei Zhang, Lei Tai, Joschka Boedecker, Wolfram Burgard, Ming Liu
opponent: Group 11


April 23

Group 6
"Learning a Multi-View Stereo Machine", A. Kar, C. Häne, J. Malik, Proc. Neural Information Processing Systems (NIPS), 2017
opponent: Group 12

Group 11
“OctNet: Learning Deep 3D Representations at High Resolutions”, Gernot Riegler, Ali Osman Ulusoy, Andreas Geiger, CVPR 2017
opponent: Group 13

Group 18
“PolyFit: Polygonal Surface Reconstruction From Point Clouds”, Liangliang Nan; Peter Wonka, ICCV 2017
opponent: Group 14


April 30

Group 22
“Fine-To-Coarse Global Registration of RGB-D Scans”, Maciej Halber, Thomas Funkhouser, CVPR 2017
opponent: Group 25

Group 19
“Colored Point Cloud Registration Revisited”, Jaesik Park; Qian-Yi Zhou; Vladlen Koltun, ICCV 2017
opponent: Group 17

Group 23
“SDF-2-SDF Registration for Real-Time 3D Reconstruction from RGB-D Data”, Miroslava Slavcheva, Wadim Kehl, Nassir Navab, Slobodan Ilic, ICCV 2017
opponent: Group 18

Group 21
“UltraStereo: Efficient Learning-based Matching for Active Stereo Systems”, Fanello et al., CVPR 2017
opponent: Group 20


May 07

Group 13
“Semantic Multi-View Stereo: Jointly Estimating Objects and Voxels” Ali Osman Ulusoy, Michael J. Black, Andreas Geiger, CVPR 2017
opponent: Group 21

Group 15
“Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation”, Kamnitsas et al.
opponent: Group 22

Group 20
“Turning Corners into Cameras: Principles and Methods”, Bouman et al., ICCV 2017
opponent: Group 24

Group 26
“Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs”, Maxim Tatarchenko, Alexey Dosovitskiy, Thomas Brox, ICCV 2017
opponent: Group 15


May 14

Group 12
“Turning an Urban Scene Video Into a Cinemagraph”, Hang Yan, Yebin Liu, Yasutaka Furukawa, CVPR 2017
opponent: Group 19

Group 24
“4D Temporally Coherent Dynamic Light-field Video” Armin Mustafa, Marco Volino, Jean-Yves Guillemaut and Adrian Hilton to appear at 3D Vision (3DV) 2017.
opponent: Group 26

Group 4
“Killingfusion: Non-rigid 3d reconstruction without correspondences” Miroslava Slavcheva, Maximilian Baust, Daniel Cremers, Slobodan Ilic, CVPR 2017.
opponent: Group 27
Group 25
“Multi-View Dynamic Shape Refinement Using Local Temporal Integration”, Vincent Leroy, Jean-Sebastien Franco, Edmond Boyer, ICCV 2017
opponent: Group 23


© CVG, ETH Zürich lm@inf.ethz.ch