Different implementations are described, in particular, implementations for coding and decoding a scalable stream comprising a base layer and at least one enhancement layer. For example, one method provides for decoding a first part of the enhancement layer relating to a group of blocks into decoded enhancement data which comprise at least one item of information for identifying at least one region of the reconstructed at least one image and obtaining residues for at least one block of the group of blocks from a second part of the enhancement layer.