Is vanishing KL a problem in vision based VAEs as well?

I came across some work on the problem of a vanishing KL contrbution in Variational Auto Encoders Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing. This work particularly is in the NLP space where they use recurrent neural networks to model sentences which yields to the vanishing KL term problem.

I wonder if there is a similar issue when working with convolutional networks and images.

Cheers