In (Mishra et al. 2020), the authors analyze a set of users' internet traffic for more than 100 days. They observed a little more than 11% of the 34,488 IP addresses they collected were present for more than a month. Many of them were reused throughout the whole experience, making long-term tracking of users possible.
The study also shows that 93% of users had a unique fixed set of IP addresses during the whole experiment, making it easy to track them between home, work, etc.
It seems from this analysis that IP address-based tracking of users is still relevant in 2020 and not defended against systematically.
The only easy way that comes to mind for the general public to prevent IP tracking is a VPN. But it is certainly not perfect either, and not sufficient to avoid all forms of online tracking.