I've looked into creating a flame graph visualization for PostgreSQL EXPLAIN output before, but CTEs that are scanned multiple times complicate things a bit. That's because the first scan on a CTE node will cause the CTE query to be executed, while further scans will simply replay the cached result-set from the first execution.

I'm sure these problems can be overcome, but it's a bit more complicated than I had imagined when I tried to do it myself. I also suspected nested-loop-joins on CTEs could further complicate the flame graph construction.