Speakers
Boyd Fowler
Google Research
Talks
| Speaker | Title |
| Noah Snavely | Geometry Beyond 3D Slide |
| Raquel Urtasun | Visual Scene Understanding for Autonomous Driving Slide |
| Leonidas J. Guibas | Information Transport in 2D and 3D Between Visual Media Slide |
| Alyosha Efros | Visual Understanding without Naming: using 3D to bypass the Language Bottleneck Slide |
| Kari Pulli | DT-SLAM: Deferred Triangulation for Robust SLAM Slide, Note |
| Martial Hebert | Using 3D data for image interpretation and geometric reasoning Slide |
| Gary Bradski | From OpenCV to Robotics and Augmented Reality Slide |
| Yuanqing Lin | Building Blocks for Visual 3D Scene Understanding towards Autonomous Driving Slide |
| Jianxiong Xiao | A Big 3D Data Approach to Scene Understanding Slide |
Demos
| Presenters | Title |
| Computer Vision Research for Amazon | A9: Visual Search on Amazon Mobile |
| The Visual Computing & Learning Group and the Flickr Vision Team | Large Scale Visual Recognition at Yahoo! |
| Meng Wang | |
| James Hegarty | Darkroom: Compiling High-Level Image Processing Code into Hardware Pipelines |
| Ky Waegel | 3D reconstruction of spaces with Matterport |
Posters
| Sponsors | |
| Amazon | Visual Search Solutions for Amazon |
| ebay | HD-CNN: Hierarchical Deep Convolutional Neural Network for Image Classification |
| Scene Understanding | |
| Manolis Savva | Learning Object Interaction Maps from Observations |
| Tianqiang liu, Siddhartha Chaudhuri, Vladmir Kim, Qixing Huang, Niloy J. Mitra, Thomas Funkhouser | Creating Consistent Scene Graphs Using a Probabilistic Grammar |
| Vladimir Kim | Shape2Pose: Human-Centric Shape Analysis |
| Richard Zhang | Sensor Fusion for Semantic Segmentation of Urban Scenes |
| 3D Reconstruction | |
| Chelhwon Kim | Planar Structures from Line Correspondences in a Manhattan World |
| Ashish Goel, Hardik Kabaria, Kristen Lisa Moore | 3D Reconstruction, Segmentation and Classification of Corals from Aerial Images |
| Ryan Crabb, Roberto Manduchi | Time-of-Flight Phase Unwrapping with Illumination and Surface Modeling |
| Matthias Niessner | Shading-based Refinement on Signed Distance Functions for Real-time 3D Reconstruction |
| Hao Su, Qixing Huang, Niloy Mitra, Yangyan Li, Leonidas Guibas | Estimating Image Depth using Shape Collections |
| Tracking and Motion | |
| David Held, Jesse Levinson, Sebastian Thrun, Silvio Savarese | Combining 3D Shape, Color, and Motion for Robust Anytime Tracking |
| Francesco Castaldo | Bayesian Tracking and Interaction Analysis for Maritime Situational Awareness |
| Yu Xiang | Monocular Multiview Object Tracking with 3D Aspect Parts |
| Erik Learned-Miller | Coherent motion segmentation in moving camera videos using optical flow orientations |
| Object Recognition | |
| Shuran Song | Sliding Shapes for 3D Object Detection in Depth Images |
| Will Y. Zou, Xiaoyu Wang, Miao Sun, Yuanqing Lin | Generic Object Detection with Dense Neural Patterns and Regionlets |
| Roozbeh Mottaghi | Beyond PASCAL: A Benchmark for 3D Object Detection in the Wild |
| Applications | |
| Roshni Cooper | Exploring the Nervous System More Effectively with Electrical Engineering: Employing Computer Vision to Accelerate Synaptic Research in C. elegans |
| Amrit Saxena | Leveraging Computer Vision Priciples for Image-Based Shoe Recommendation |
| Subhashini Venugopalan | Integrating Language and Vision to Generate Natural Language Descriptions of Videos in the Wild |
| Daniela Ushizima, Talita Perciano and Harinarayan Krishnan | Scaling image processing for scientific data |
| G. Fusco, H. Shen and J. Coughlan | Self-Localization at Street Intersections from Street Panoramas |
| Nikhil Naik, Jade Philipoom, Ramesh Raskar, Cesar Hidalgo | Streetscore - predicting the perceived safety of one million streetscapes |