The recurrent presence of clouds and clouds shadows in aerial or remotely sensed images is an awkward
problem that severely limits the regular exploitations capability of these images. Removing cloud-contaminated
portions of the image and then filling in the missing data represent an important photo editing cumbersome task.
The intent of this work is to propose a technique for the reconstruction of areas obscured by clouds in a remotely
sensed image. To this end, a new efficient reconstruction technique for missing data synthesis is presented.
This technique is based on the Bandelet transform and the multiscale geometrical grouping. It consists of two
steps. In the first step, the curves of geometric flow of different zones of the image are determined by using the
Bandelet transform with multiscale grouping. This step allows a better representation of the multiscale geometry
of the image's structures. Having well represented this geometry, the information inside the cloud-contaminated
zone is synthesized by propagating the geometrical flow curves inside that zone. This step is accomplished by
minimizing a functional whose role is to reconstruct the missing or cloud contaminated zone independently of
the size and topology of the reconstruction or inpainting domain. Thus, the flow lines are well tied inside the
cloud-contaminated zone. The proposed technique is illustrated with some examples on processing multispectral
aerial images. The obtained results are compared with those obtained by other clouds removal techniques.