
Within the recent decade, reconstruction of real world scenes gained continuously more importance. For realistic reconstructions both, the geometry and the textures, are important. We present a general algorithm for reconstructing textures from an image sequence of flat patches, where the angle between the patch normal and the view direction of the observing cameras could be close to 90. In such case the image of the patch in the camera frames collapses to just a few pixel rows, and most of the algorithms used today will fail. The method we present uses an analysis-by-synthesis approach for reconstructing the texture by combining information from all input images. In each step, the previously reconstructed texture is tested by using it for rendering artificial input images which are then compared to the real ones. If they are not equal, we use the difference for calculating an update to the existent texture. For this update we employ a back projection approach that produces excellent reconstructions in only a few iteration steps.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
