Abstract
We describe a novel approach to view interpolation from image
sequences based on probabilistic depth carving. This builds a
multivalued representation of depth for novel views consisting of
likelihoods of depth samples corresponding to either opaque or free
space points. The likelihoods are obtained from iterative
probabilistic combination of local disparity estimates about a subset
of reference frames. This avoids the difficult problem of
correspondence matching across distant views and leads to an explicit
representation of occlusion. Novel views are generated by combining
pixel values from the reference frames based on estimates of surface
points within the likelihood representation. Efficient implementation
is achieved using a multiresolution framework. Results of experiments
on real image sequences show that the technique is effective.
Translated title of the contribution | Interpolating Novel Views from Image Sequences by Probabilistic Depth carving |
---|---|
Original language | English |
Pages (from-to) | 379 - 390 |
Number of pages | 12 |
Journal | Lecture Notes in Computer Science |
Volume | 3022 |
Publication status | Published - May 2004 |
Bibliographical note
Editors: Pajdla, T and Matas, JISBN: 3540219835
Publisher: Springer
Name and Venue of Conference: 8th European Conference on Computer Vision (ECCV 2004), Prague, 11-14 May
Other: http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=2000105