xandergos

I might improve terrain diffusion as a whole but probably not going to work on porting it to all kinds of games. It’s pretty hard to develop it as a standalone

Very excited to share this paper I've been working on independently for over a year! It started as a research project for fun in college, using an RTX 3090 I bought from my internship at Walmart. The goal was to produce an AI terrain generator that functioned like procedural noise, could run locally, and looked beautiful. Turns out this problem was more unsolved than I thought, and now it's at SIGGRAPH 2026.

Happy to answer any questions!

I've thought about this before, and I think there is some way you could find to do it. For example, you could generate on the mercator projection of the world, and then un-project. But the mercator distorts horizontal length approaching the poles. I think it would be complex to implement, but you could use larger windows closer to the poles to negate this.

Could be! I think maps are definitely the most interesting direction for future research to take.

No worries! It's worded fine as-is given the restrictions. Just wanted to clear up any misunderstandings.

Hi everyone, I wrote this paper. Cool to see it has been posted here already.

I want to clarify some points on things other people have mentioned:

- This architecture is not as fast as Perlin noise. IMO it is unlikely we will see any significant improvement on Perlin noise without a significant increase in compute, at least for most applications. Nonetheless, this system is not too slow for real-time use. In the Minecraft integration, for instance, the bottleneck in generation speed is by far Minecraft's own generation logic (on one RTX 3090 Ti).

- I agree that this is not "production-ready" for most tasks. The main issue is that (1) terrain is generated at realistic scales, which are too big for most applications, and (2) the only control the user has is the initial elevation map, which is very coarse. Thankfully, I expect both of these issues to be fixed pretty quickly. (1) is more specific to terrain generation, but I have a number of ideas on how to fix it. (2) is mostly an issue simply because I did not have the time to engineer a system with this many features (and as-is, the system is quite dense). I believe a lot of existing work on diffusion conditioning could be adapted here.

- The post title misses one key part of the paper title: "in Infinite, Real-Time Terrain Generation." I don't expect this to replace perlin noise in other applications. And for bounded generation, manual workflows are still superior.

- The top level input is perlin noise because it is genuinely the best tool for generating terrain at continental scale. If I had more time on my hands, I would like to use some sort of plate tectonics simulator to generate that layout, but for something simple, reasonably realistic, and infinite, perlin noise is pretty much unbeatable. Even learned methods perform on-par with perlin noise at this scale because the data is so simple.