Method and apparatus for encoding and decoding image by using large transform unit

1. A method of decoding an image, the method comprising:

obtaining quantized transformation coefficients of at least one transformation unit in a coding unit of the image;

performing inverse-quantization and inverse-transformation on the quantized transformation coefficients of the at least one transformation unit to obtain residuals;

performing inter prediction for at least one prediction unit in the coding unit to generate a predictor; and

restoring the image by using the residuals and the predictor,

wherein, when a prediction mode is an inter prediction mode, not an intra prediction mode, a size of the at least one transformation unit in the coding unit is determined independently from a size of the at least one prediction unit in the coding unit,

wherein the image is split into a plurality of maximum coding units, according to information about a maximum size of the coding unit, and

wherein a maximum coding unit among the plurality of maximum coding units is hierarchically split into one or more coding units including at least one of the coding unit of a current depth and a coding unit of a lower depth, and

when split information indicates a split for the current death, the coding unit of the current depth is split into four rectangular coding units of the lower depth, independently from neighboring coding units.

2. The method of claim 1 , wherein the performing inverse-quantization and inverse-transformation comprises determining a size of the at least one transformation unit based on whether the prediction mode is the inter prediction mode or the intra prediction mode.

3. The method of claim 1 , wherein the inverse-transformation comprises determining the at least one transformation unit whose size is larger than a size of the at least one prediction unit in the at least one prediction unit.