In my opinion, any game featuring large-scale, realistic terrain would benefit from a tool like this. You simply can't hand-craft every ridge on a mountain range at that scale. Unless you're recreating a real-world location using satellite and LIDAR height data, procedural filters are the only way to achieve that level of geological detail efficiently.
I imagine lots of games do already, but offline. Most games don’t have gameplay that requires real-time terrain generation. The idea of generating terrain procedurally is not new, but this technique that gets a great-looking erosion effect in real time is.
It’s fascinating to see the bridge between academic research and industry application here. While Image Matting is a massive research area in Computer Vision, academia often focuses on solving perfect 'benchmarks.' Corridor Crew effectively took that foundational research, like neural unmixing and synthetic training, and adapted it to solve the 'messy' reality of production, like tracking markers and motion blur. It’s a great example of using open-source deep learning resources to build a tool that prioritized workflow over just a high accuracy score.
Well this is just a personal website, so it is has much (or as little) information as the owner wants to put up. The legal notice page (in German) tells you it's the site of a certain Dr. Ulrich Deuschle: https://www.udeuschle.de/impressum.html
LLM can translate in the style you want them to. You can make them translate more creatively or just translate word by word. I even think you can make them explain their choice of translation and help you proof-read the result.
There's no way to do it traditionally. Your request would need the algorithm to understand the content of the image. Deep learning based image vectorization probably has a similar objective.
