• Publications
  • Influence
Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes
  • A. Johnson, M. Hebert
  • Computer Science, Mathematics
  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 1 May 1999
A compression scheme for spin images that results in efficient multiple object recognition which is verified with results showing the simultaneous recognition of multiple objects from a library of 20 models. Expand
A spectral technique for correspondence problems using pairwise constraints
  • M. Leordeanu, M. Hebert
  • Mathematics, Computer Science
  • Tenth IEEE International Conference on Computer…
  • 17 October 2005
An efficient spectral method for finding consistent correspondences between two sets of features by using the principal eigenvector of M and imposing the mapping constraints required by the overall correspondence mapping. Expand
Toward Objective Evaluation of Image Segmentation Algorithms
It is demonstrated how a recently proposed measure of similarity, the normalized probabilistic rand (NPR) index, can be used to perform a quantitative comparison between image segmentation algorithms using a hand-labeled set of ground-truth segmentations. Expand
Recovering Surface Layout from an Image
This paper takes the first step towards constructing the surface layout, a labeling of the image intogeometric classes, to learn appearance-based models of these geometric classes, which coarsely describe the 3D scene orientation of each image region. Expand
Cross-Stitch Networks for Multi-task Learning
This paper proposes a principled approach to learn shared representations in Convolutional Networks using multitask learning using a new sharing unit: "cross-stitch" unit that combines the activations from multiple networks and can be trained end-to-end. Expand
An Integer Projected Fixed Point Method for Graph Matching and MAP Inference
This paper argues that the stage in which a discrete solution is found is crucial for good performance and proposes an efficient algorithm, with climbing and convergence properties, that optimizes in the discrete domain the quadratic score, and it gives excellent results either by itself or by starting from the solution returned by any graph matching algorithm. Expand
PCN: Point Completion Network
The experiments show that PCN produces dense, complete point clouds with realistic structures in the missing regions on inputs with various levels of incompleteness and noise, including cars from LiDAR scans in the KITTI dataset. Expand
Discriminative Random Fields
This work presents Discriminative Random Fields (DRFs) to model spatial interactions in images in a discriminative framework based on the concept of Conditional Random Fields proposed by lafferty et al.(2001). Expand
Autonomous Driving in Urban Environments: Boss and the Urban Challenge
This dissertation aims to provide a history of web exceptionalism from 1989 to 2002, a period chosen in order to explore its roots as well as specific cases up to and including the year in which descriptions of “Web 2.0” began to circulate. Expand
Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification
This paper forms an approach for learning a visual representation from the raw spatiotemporal signals in videos using a Convolutional Neural Network, and shows that this method captures information that is temporally varying, such as human pose. Expand