A video encoding method and apparatus are provided. The video encoding method includes determining whether a current block includes an affine-transformation object having an affine transformation; if the current block includes an affine-transformation object, generating a prediction block by performing affine transformation-based motion compensation on the current block in consideration of an affine transformation of the affine-transformation object; and if the current block does not include any affine-transformation object, generating a prediction block by performing motion vector-based motion compensation on the current block using a motion vector of the current block. Therefore, it is possible to achieve high video encoding/decoding efficiency even when a block to be encoded or decoded includes an affine transformation.