Intra-predictive transforms are a kind of block-based transforms that can exploit both the intra- and inter-block correlations. This paper analyzes the coding gains of intra-predictive transforms for the Gaussian process. The tight upper bound of the coding gain is derived, which is shown to be better than both the discrete cosine transform and the Karhunen Lo`eve transform. The optimal intra-predictive transform that achieves the upper bound is also presented. Actual coding results on images verify the effectiveness of the optimal intra-predictive transform.