C
Charles R. Dyer
Researcher at University of Wisconsin-Madison
Publications - 141
Citations - 10220
Charles R. Dyer is an academic researcher from University of Wisconsin-Madison. The author has contributed to research in topics: Motion estimation & Motion field. The author has an hindex of 43, co-authored 141 publications receiving 9919 citations. Previous affiliations of Charles R. Dyer include University of Wisconsin System & University of Maryland, College Park.
Papers
More filters
Proceedings ArticleDOI
Photorealistic scene reconstruction by voxel coloring
Steven M. Seitz,Charles R. Dyer +1 more
TL;DR: In this article, a novel scene reconstruction technique is presented, which avoids image correspondence problems by working in a discretized scene space whose voxels are traversed in a fixed visibility ordering.
Journal ArticleDOI
Experiments on Picture Representation Using Regular Decomposition
Allen Klinger,Charles R. Dyer +1 more
TL;DR: A regular decomposition of picture area into successively smaller quadrants is defined, which involves logarithmic search, and the resulting picture representation is shown to enable rapid access of image data without regard to position, efficient storage, and approximate structural descriptions of constituent patterns.
Journal ArticleDOI
Visibility, occlusion, and the aspect graph
Harry Plantinga,Charles R. Dyer +1 more
TL;DR: This chapter studies the ways in which the topology of the image of a polyhedron changes with changing viewpoint, and presents tight bounds on the maximum size of the VSP and the aspect graph and gives algorithms for their construction.
Journal ArticleDOI
Learning from examples in the small sample case: face expression recognition
Guodong Guo,Charles R. Dyer +1 more
TL;DR: A new technique based on linear programming for both feature selection and classifier training is introduced and a pairwise framework for feature selection, instead of using all classes simultaneously, is presented.
Book ChapterDOI
Volumetric Scene Reconstruction from Multiple Views
TL;DR: A review of methods for volumetric scene reconstruction from multiple views is presented in this paper, where occupancy descriptions of the voxels in a scene volume are constructed using shape-from-silhouette techniques for binary images, and shape from-photo-consistency combined with visibility testing for color images.