We propose a new algorithm for compressing three-dimensional triangular mesh data used for representing surfaces. We apply the Estimation-Quantization (EQ) algorithm originally designed for still image compression to the normal mesh wavelet coefficients. The EQ algorithm models the wavelet coefficients as a Gaussian random field with slowly varying standard deviation. By designing the quantizers in a rate-distortion optimal fashion, we improve upon the recently proposed zerotree normal mesh compression algorithm by 0.5 to 1 dB in distortion.