CVPR 2014 Tutorial

Dense Image Correspondences for Computer Vision

Ce Liu1   Michael Rubinstein1   Jaechul Kim2   Zhuowen Tu3   

1Microsoft Research     2Amazon     3UCSD


8:30am~5pm, June 23, 2014


C111-112 Columbus Convention Center, Columbus Ohio


Correspondence, namely how pixels in one image correspond to pixels in another image, is a fundamental problem in computer vision. Although correspondence has been mostly used for analyzing transformations between images from one scene, a new era has started recently when correspondence can be established across different scenes. In this tutorial, we will give an overview of dense correspondence algorithms for aligning images from different scenes. We will survey a variety of representations, including pixels (SIFT flow, Non-Rigid Dense Correspondence), semantic segments (layer flow) and image pyramid (deformable spatial pyramid). These dense alignment algorithms are powerful tools to analyze images and videos. We can not only transform information such as semantic labels, image details and geometry from images and videos in a labeled dataset, but also analyze an entire image database as a whole via information propagation. Recent advances on scene parsing, 2D video to 3D, annotation propagation (image to text), object discovery, co-segmentation, image hallucination, and biomedical image analysis demonstrate that across-scene correspondence can be a fundamental building block for computer vision.

Tutorial Schedule

Time Speaker Title
8:30 ~ 9:30am Ce Liu Dense Image Correspondences: Introduction
9:30 ~ 10:00am Jaechul Kim Deformable Spatial Pyramid Matching
10:00 ~ 10:30am Break
10:30 ~ 11:00am Marshall Tappen  
11:00 ~ 11:30am Zhuowen Tu Scale-Space SIFT Flow and Non-Parametric Models for Image Correspondences
11:30 ~ 12:00pm Tal Hassner Scale-less Dense Correspondences
12:00 ~ 1:30pm Lunch break
1:30 ~ 2:10pm Michael Rubinstein Joint Inference in Image Databases via Dense Correspondences
2:10 ~ 2:30pm Joseph Lim Ground-truth image dense correspondence database
2:30 ~ 3:00pm Ce Liu Depth-transfer for video
3:00 ~ 3:30pm Break
3:30 ~ 4:00pm Eyal Ofek
4:00 ~ 4:30pm Philip Isola Scene Collaging: Dense Correspondence for Scenes with Layers 
4:30 ~ 5:00pm Ce Liu Wrap-up