In the CNN, how do you concatenate intermediate outputs coming from different amounts of pooling?

I'm trying to reimplement the CNN part but I'm wondering: how do you concatenate the intermediate results coming from different layers, some with and some without pooling? For example, Fig. 7 in the paper or the image in the readme both show that some layers take as input the concat of the intermediate output of a max pooling layer and some other conv layer before it. But if you assume that you have inputs of 224x224, strides=1 in the convs and the right amount of padding, the output of a conv layer will be n_filtersx224x224, while the pooling output (assuming stride 2) will be n_filtersx112x112. How do you concatenate the two intermediate outputs?

The issue points to Fig. 7 in the paper and the image in the README; start by comparing those diagrams with the repository's CNN implementation in Python/PyTorch. Trace the tensor shapes through the pooled and unpooled paths to explain how the concatenation is made possible. Done means the issue or README contains a clear, dimensionally consistent explanation.

Written by the indexing model from the issue text.