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 21

Group 15
Heinly et al., Reconstructing the World in Six Days
opponent: Group 3

Group 16
Nurutdinova and Fitzgibbon, Towards Pointless Structure from Motion: 3D reconstruction and camera parameters from general 3D curves
opponent: Group 8

April 04

Group 5
Jure Žbontar and Yann LeCun, Computing the Stereo Matching Cost With a Convolutional Neural Network
opponent: Group 1

Group 6
Alexey Dosovitskiy et al., FlowNet: Learning Optical Flow with Convolutional Networks
opponent: Group 10

Group 8
Stephan Schraml et al., Event-Driven Stereo Matching for Real-Time 3D Panoramic Vision
opponent: Group 11

April 11

Group 2
Thomas Whelan et al., ElasticFusion: Dense SLAM Without A Pose Graph
opponent: Group 6

Group 12
Christian Kerl et al., Dense Continuous-Time Tracking and Mapping With Rolling Shutter RGB-D Cameras
opponent: Group 7

Group 17
Bryan Klingner et al., Street View Motion-from-Structure-from-Motion
opponent: Group 9

April 25

Group 1
Benjamin Ummenhofer and Thomas Brox, Global, Dense Multiscale Reconstruction for a Billion Points
opponent: Group 4

Group 14
Sungjoon Choi et al., Robust Reconstruction of Indoor Scenes
opponent: Group 13

May 2

Group 9
Mingsong Dou et al., 3D Scanning Deformable Objects with a Single RGBD Sensor
opponent: Group 5

Group 11
Qian-Yi Zhou and Vladlen Koltun, Color Map Optimization for 3D Reconstruction with Consumer Depth Cameras
opponent: Group 16

May 9

Group 7
Satoshi Ikehata et al., Structured Indoor Modeling
opponent: Group 12

Group 10
Chen Zhou et al., Exploiting Object Similarity in 3D Reconstruction
opponent: Group 15

Group 13
Christian Hane et al., Joint 3D Scene Reconstruction and Class Segmentation
opponent: Group 17

May 23

Group 3
Richard A. Newcombe et al., DynamicFusion: Reconstruction and Tracking of Non-Rigid Scenes in Real-Time
opponent: Group 2

Group 4
Enliang Zheng et al., Sparse Dynamic 3D Reconstruction from Unsynchronized Videos
opponent: Group 14