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 18

Group 16
Schönberger & Frahm "Structure-from-motion revisited." CVPR 2016
opponent: Group 14

Group 17
Mishkin et al. "Repeatability is not enough: Learning affine regions via discriminability." ECCV 2018
opponent: Group 8

Group 23
Herrmann et al. "Robust image stitching with multiple registrations." ECCV 2018
opponent: Group 2


March 25

Group 9
Kendall et al. "End-to-end learning of geometry and context for deep stereo regression." ICCV 2017
opponent: Group 22

Group 18
Ummenhofer et al. "Demon: Depth and motion network for learning monocular stereo." CVPR 2017
opponent: Group 17

Group 21
Schönberger et al. "Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching." ECCV 2018
opponent: Group 12


April 01

Group 1
Newcombe et al. "DTAM: Dense tracking and mapping in real-time." ICCV 2011
opponent: Group 24

Group 6
Engel et al. “DSO: Direct Sparse Odometry”, TPAMI 2018
opponent: Group 4

Group 22
Gallego et al. “Event-based, 6-DOF Camera Tracking from Photometric Depth Maps”, TPAMI 2017
opponent: Group 21


April 15

Group 2
Huang et al. " DeepMVS: Learning Multi-view Stereopsis", CVPR 2018
opponent: Group 1

Group 5
Groueix et al. “A Papier-Mâché Approach to Learning 3D Surface Generation”, CVPR 2018
opponent: Group 3

Group 20
Kar et al. “Learning a Multi-View Stereo Machine”, NIPS 2017
opponent: Group 19


April 29

Group 8
Shi et al. “PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction”, ECCV2018
opponent: Group 7

Group 10
Newcombe et al. “Dynamicfusion: Reconstruction and tracking of non-rigid scenes in real-time”, CVPR 2015
opponent: Group 6

Group 19
Zheng et al. “HybridFusion: real-time performance capture using a single depth sensor and sparse IMUs”, ECCV 2018
opponent: Group 20


May 06

Group 3
Senanayake et al. “Learning Highly Dynamic Environments with Stochastic Variational Inference.” ICRA 2017
opponent: Group 5

Group 4
Dai et al. “ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans”, CVPR 2018
opponent: Group 18

Group 15
Simon et al. “Hand Keypoint Detection in Single Images using Multiview Bootstrapping”, CVPR 2017
opponent: Group 13


May 13

Group 12
von Marcard et al. “ Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera”, ECCV 2018
opponent: Group 11

Group 13
Kanazawa et al. “End-to-end Recovery of Human Shape and Pose” CVPR 2018
opponent: Group 15

Group 14
Gao et al. “Im2Flow: Motion Hallucination from Static Images for Action Recognition” CVPR 2018
opponent: Group 16

May 20

Group 7
Schops et al. “Real-Time View Correction for Mobile Devices”, TVCG 2017
opponent: Group 9

Group 11
Brachmann et al. “DSAC - Differentiable RANSAC for Camera Localization” CVPR 2017
opponent: Group 10

Group 24
Insafutdinov and Dosovitskiy “Unsupervised Learning of Shape and Pose with Differentiable Point Clouds” NIPS 2018
opponent: Group 23


© CVG, ETH Zürich lm@inf.ethz.ch