When is the shape of a scene unique given its light-field: A fundamental theorem of 3D vision?

Please use this identifier to cite or link to this item: https://doi.org/10.1109/TPAMI.2003.1159949

Title:	When is the shape of a scene unique given its light-field: A fundamental theorem of 3D vision?
Authors:	Baker, S. Sim, T. Kanade, T.
Keywords:	3D shape reconstruction Light-fields Shape-from-silhouette Stereo The plenoptic function Uniqueness
Issue Date:	2003
Citation:	Baker, S., Sim, T., Kanade, T. (2003). When is the shape of a scene unique given its light-field: A fundamental theorem of 3D vision?. IEEE Transactions on Pattern Analysis and Machine Intelligence 25 (1) : 100-109. ScholarBank@NUS Repository. https://doi.org/10.1109/TPAMI.2003.1159949
Abstract:	The complete set of measurements that could ever be used by a passive 3D vision algorithm is the plenoptic function or light-field. We give a concise characterization of when the light-field of a Lambertian scene uniquely determines its shape and, conversely, when the shape is inherently ambiguous. In particular, we show that stereo computed from the light-field is ambiguous if and only if the scene is radiating light of a constant intensity (and color, etc.) over an extended region.
Source Title:	IEEE Transactions on Pattern Analysis and Machine Intelligence
URI:	http://scholarbank.nus.edu.sg/handle/10635/38900
ISSN:	01628828
DOI:	10.1109/TPAMI.2003.1159949
Appears in Collections:	Staff Publications

There are no files associated with this item.

Check