Skip to content

Instantly share code, notes, and snippets.

@yairomer
Last active April 17, 2018 13:00
Show Gist options
  • Save yairomer/1323e1fa6b3d2b42e65764bc9956785f to your computer and use it in GitHub Desktop.
Save yairomer/1323e1fa6b3d2b42e65764bc9956785f to your computer and use it in GitHub Desktop.
CVPR 2017

Highlights

Friday (21/7)

Am - tutorial

Pm - tutorial

Full day - workshop


Saturday (22/7)

Morning spotlight - Machine Learning

  • Convolutional Neural Network Architecture for Geometric Matching - Ignacio Rocco, Relja Arandjelović, Josef Sivic (2704)
  • PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation - Charles R. Qi, Hao Su, Kaichun Mo, Leonidas J. Guibas

Morning spotlight - 3D Vision

  • Global Hypothesis Generation for 6D Object Pose Estimation - Frank Michel, Alexander Kirillov, Eric Brachmann, Alexander Krull, Stefan Gumhold, Bogdan Savchynskyy, Carsten Rother (147)
  • A Practical Method for Fully Automatic Intrinsic Camera Calibration Using Directionally Encoded Light - Mahdi Abbaspour Tehrani, Thabo Beeler, Anselm Grundhöfer (308)
  • Dynamic Time-Of-Flight - Michael Schober, Amit Adam, Omer Yair, Shai Mazor, Sebastian Nowozin (2685)
  • Semantic Scene Completion From a Single Depth Image - Shuran Song, Fisher Yu, Andy Zeng, Angel X. Chang, Manolis Savva, Thomas Funkhouser
  • 3DMatch: Learning Local Geometric Descriptors From RGB-D Reconstructions - Andy Zeng, Shuran Song, Matthias Nießner, Matthew Fisher, Jianxiong Xiao, Thomas Funkhouser
  • On-The-Fly Adaptation of Regression Forests for Online Camera Relocalisation - Tommaso Cavallari, Stuart Golodetz, Nicholas A. Lord, Julien Valentin, Luigi Di Stefano, Philip H. S. Torr

Morning spotlight - Low & Mid Level Vision

Morning posters

Afternoon spotlight - Object Recognition & Scene Understanding - Computer Vision & Language

Afternoon spotlight - Analyzing Humans 1

Afternoon spotlight - Image Motion & Tracking; Video Analysis

  • Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data - Joel Janai, Fatma Güney, Jonas Wulff, Michael J. Black, Andreas Geiger

Afternoon posters

Keynote

James J. DiCarlo (Institute for Brain Research, MIT.) - The Science of Natural intelligence (NI): Reverse Engineering Primate Visual Perception


Sunday (23/7)

Morning spotlight - Machine Learning

  • Semi-Supervised Deep Learning for Monocular Depth Map Prediction   Yevhen Kuznietsov, Jörg Stückler, Bastian Leib

  • Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach Giorgio Patrini, Alessandro Rozza, Aditya Krishna Menon, Richard Nock, Lizhen Qu (best paper)

  • Densely Connected Convolutional Networks Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger (best paper)

Morning spotlight - Computational Photography

  • Unrolling the Shutter: CNN to Correct Motion Distortions - Vijay Rengarajan, Yogesh Balaji, A. N. Rajagopalan
  • Light Field Blind Motion Deblurring - Pratul P. Srinivasan, Ren Ng, Ravi Ramamoorthi

Morning spotlight - 3D Vision

  • HSfM: Hybrid Structure-from-Motion - Hainan Cui, Xiang Gao, Shuhan Shen, Zhanyi Hu
  • Efficient Global Point Cloud Alignment Using Bayesian Nonparametric Mixtures - Julian Straub, Trevor Campbell, Jonathan P. How, John W. Fisher III
  • A New Rank Constraint on Multi-View Fundamental Matrices, and Its Application to Camera Location Recovery - Soumyadip Sengupta, Tal Amir, Meirav Galun, Tom Goldstein, David W. Jacobs, Amit Singer, Ronen Basri
  • Noise Robust Depth From Focus Using a Ring Difference Filter - Jaeheung Surh, Hae-Gon Jeon, Yunwon Park, Sunghoon Im, Hyowon Ha, In So Kweon
  • Group-Wise Point-Set Registration Based on Rényi's Second Order Entropy - Luis G. Sanchez Giraldo, Erion Hasanbelliu, Murali Rao, Jose C. Principe
  • A Point Set Generation Network for 3D Object Reconstruction From a Single Image - Haoqiang Fan, Hao Su, Leonidas J. Guibas
  • 3D Point Cloud Registration for Localization Using a Deep Neural Network Auto-Encoder - Gil Elbaz, Tamar Avraham, Anath Fischer
  • DSAC - Differentiable RANSAC for Camera Localization - Eric Brachmann, Alexander Krull, Sebastian Nowozin, Jamie Shotton, Frank Michel, Stefan Gumhold, Carsten Rother

Afternoon spotlight - Object Recognition & Scene Understanding

Afternoon spotlight - Analyzing Humans

Afternoon spotlight - Applications

Afternoon posters

Keynote

Harry Shum (Artificial Intelligence and Research Group, Microsoft) - Commercializing computer vision: Success stories and lessons learned


Monday (24/7)

spotlight - Machine Learning

  • Local Binary Convolutional Neural Networks - Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides
  • Deep Self-Taught Learning for Weakly Supervised Object Localization - Zequn Jie, Yunchao Wei, Xiaojie Jin, Jiashi Feng, Wei Liu
  • Global Optimality in Neural Network Training - Benjamin D. Haeffele, René Vidal

spotlight - Object Recognition & Scene Understanding

posters


Tuesday (25/7)

Morning spotlight - Machine Learning

Morning spotlight - Analyzing Humans with 3D Vision

Morning posters

Afternoon spotlight - Object Recognition & Scene Understanding

  • YOLO9000: Better, Faster, Stronger - Joseph Redmon, Ali Farhadi

Afternoon spotlight - Machine Learning for 3D Vision

  • UltraStereo: Efficient Learning-Based Matching for Active Stereo Systems - Sean Ryan Fanello, Julien Valentin, Christoph Rhemann, Adarsh Kowdle, Vladimir Tankovich, Philip Davidson, Shahram Izadi
  • Geometric Loss Functions for Camera Pose Regression With Deep Learning - Alex Kendall, Roberto Cipolla
  • CNN-SLAM: Real-Time Dense Monocular SLAM With Learned Depth Prediction - Keisuke Tateno, Federico Tombari, Iro Laina, Nassir Navab
  • Unsupervised Monocular Depth Estimation With Left-Right Consistency - Clément Godard, Oisin Mac Aodha, Gabriel J. Brostow
  • Unsupervised Learning of Depth and Ego-Motion From Video - Tinghui Zhou, Matthew Brown, Noah Snavely, David G. Lowe

Afternoon posters

  • Improved Stereo Matching With Constant Highway Networks and Reflective Confidence Learning - Amit Shaked, Lior Wolf

Keynote

Dan Jurafsky (Computer Science, Stanford ) - Extracting Social Meaning from Language


Wednesday (26/7)

Am - tutorial

Pm - tutorial

Am - full day

Full day - workshop

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment