Let me define the way I understand stochastic quantization. Stochastic quantization to me is a way of constructing infinite dimensional measures with a given "density".
Suppose we are given an action functional $S=\int L(q,v)dx$ on some infinite dimensional space. Stochastic quantization is interested in constructing the measure with "density" $$\mu(dx)=\frac{1}{Z}\exp(-S(x))D^\infty x,$$ where $D^\infty x$ is the non existent infinite dimensional Lebesgue measure and $Z$ is a normalization constant.
Stochastic quantization makes this rigorous by considering the stochastic gradient descent equation
$$\partial_t u= -\left(\frac{\delta L}{\delta q}-\nabla \cdot \frac{\delta L}{\delta v}\right)+\xi,$$
where $\xi$ is space-time white noise. If this SPDE has an invariant measure $\mu$, then $\mu$ is defined to be the measure we hoped to construct. The reason is the analogy for the invariant measure of stochastic ODEs. This all makes sense to me.
However, in what sense is this "quantization"? To me, quantization means discretization. What is being discretized in stochastic quantization?