Full-day workshop

Accepted Papers


SuperPoint: Self-Supervised Interest Point Detection and Description
Daniel DeTone*, Magic Leap; Tomasz Malisiewicz, Magic Leap, Inc.; Andrew Rabinovich, Magic Leap, Inc.

Global Pose Estimation with an Attention-based Recurrent Network
Emilio Parisotto*, Carnegie Mellon University; Devendra Singh Chaplot, Carnegie Mellon University; Jian Zhang, Apple Inc.; Ruslan Salakhutdinov, Carnegie Mellon University


Visual SLAM for Automated Driving: Exploring the Applications of Deep Learning
Senthil Yogamani*, Valeo Vision Systems; Stefan Milz, Valeo; Christian Witt, Valeo; Georg Arbeiter, Valeo; Bassam Abdallah, Valeo

Mask-SLAM: Robust feature-based monocular SLAM by masking using semantic segmentation
Masaya Kaneko*, The University of Tokyo; Kazuya Iwami, The University of Tokyo; Toru Ogawa, The University of Tokyo; Toshihiko Yamasaki, The University of Tokyo; Kiyoharu Aizawa, The University of Tokyo

Geometric Consistency for Self-Supervised End-to-End Visual Odometry
Ganesh Iyer, IIIT Hyderabad; Krishna Murthy Jatavallabhula*, Montreal Institute of Learning Algorithms (MILA); Gunshi Gupta, IIIT Hyderabad; Madhava Krishna, IIIT-Hyderabad; Liam Paull, Université de Montréal

Learning Descriptor, Confidence, and Depth Estimation in Multi-view Stereo
Sungil Choi, Yonsei University; Seungryung Kim, Yonsei University; Kihong Park, Yonsei Univ.; Kwanghoon Sohn *, Yonsei Univ.

DepthNet: A Recurrent Neural Network Architecture for Monocular Depth Prediction
Arun CS Kumar*, University of Georgia; Suchendra Bhandarkar, University of Georgia; Mukta Prasad, Trinity College, Dublin

Towards CNN map representation and compression for camera relocalisation
Luis Contreras*, National Autonomous University of Mexico, Walterio Mayol-Cuevas, University of Bristol

Monocular Depth Prediction using Generative Adversarial Networks
Arun CS Kumar*, University of Georgia; Suchendra Bhandarkar, University of Georgia; Mukta Prasad, Trinity College, Dublin

Learning 3D Scene Semantics and Structure from a Single Depth Image
Bo Yang*, University of Oxford; Zihang Lai, University of Oxford; Xianxuan Lu, University of Oxford; Shuyu Lin, University of Oxford; Hongkai Wen, University of Warwick; Andrew Markham, University of Oxford; Niki Trigoni, University of Oxford

QuadricSLAM: Constrained Dual Quadrics from Object Detections as Landmarks in Semantic SLAM (extended abstract)
Lachlan Nicholson* QUT, ACRV; Michael Milford, ACRV and QUT, Australia; Niko Suenderhauf, Queensland University of Technology