Laplacian and generalized Gaussian data arise in the transform and sub
band coding of images, This paper describes a method of rotating indep
endent, identically distributed (i.i.d.) Laplacian-like data in multip
le dimensions to Significantly improve the overload characteristics fo
r quantization, The rotation is motivated by the geometry of the Lapla
cian probability distribution, and can be achieved with only additions
and subtractions using a Walsh-Hadamard transform, Its theoretical an
d simulated results for scalar, lattice, and polar quantization are pr
esented in this paper, followed by a direct application to image compr
ession, We show that rotating the image data before quantization not o
nly improves compression performance, but also increases robustness to
the channel noise and deep fades often encountered in wireless commun
ication.