Continuous Model Synthesis

Подписаться 1,2 тыс.

Просмотров 3,6 тыс.

50% 1

Explains the second half of my PhD dissertation. How to extend model synthesis to generate complex shapes that don’t work on a regular grid. For more information see: paulmerrell.or...
References:
P. Merrell and D. Manocha. Continuous Model Synthesis. ACM Transactions on Graphics, 2008.
P. Merrell and D. Manocha. Model Synthesis: A General Procedural Modeling Algorithm. IEEE Transactions on Visualization and Computer Graphics, 2010.
P. Merrell, E. Schkufza, and V. Koltun. Computer-Generated Residential Building Layouts. ACM Transactions on Graphics, 2010.
C. Han, E. Risser, R. Ramamoorthi, and E. Grinspun. Multiscale Texture Synthesis. ACM Transactions on Graphics, 2008.

Опубликовано:

15 сен 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 16

@ciberman Год назад

Amazing work! I don't think I have a project that fit this currently but It serves as inspiration while researching about procedural house generation. Thank you a lot for your contributions!

@PaulMerrellResearch Год назад

Thank you!

@HybridLizard_com 2 года назад

I am not capable to use that knowledge, at least yet, but I like it anyway. 😅 The video and work put into making it deserves more views. Instant sub.

@georhodiumgeo9827 7 месяцев назад

Am I correct in my intuition that using parallel lines from a non-periodic tiling would be completely impossible? By its very nature I think you would run into the same precision problems you mentioned in the arbitrary points version but to be honest I'm not sure. I guess the reason I was thinking about that is because if you limit the angles of the arbitrary shapes, in any configuration they would exist in exactly that configuration at some point in the non-periodic tiling. Well any specific set of vertexes would at least. But as it's an infinite grid you couldn't find that place without rounding something. So taking from that thought, if you had a tiling that repeats every 16 parallel lines in all directions then you could "round" the arbitrary shapes onto the psudo periodic grid and get exact values of that shape now that is is locked onto the grid. That's probably not the best explanation and I don't know what I talking about but it's very interesting. At any rate thank you for that well made video and the work you have done. Every time I see wave function collapse in the wild it makes me happy. Good luck.

@PaulMerrellResearch 7 месяцев назад

I'm not sure I'm following you. For non-periodic tilings like the einstein tiling or Penrose tiling, the shapes actually fit neatly onto a regular grid. For the einstein tile, there are only three distinct edge directions, so you would only need six sets of parallel lines, and they fit on a hexagonal grid. I don't see how numeric precision problems would play into this as those are for doing exact Boolean operations, but the tiling is exact.

@bulalaish 2 года назад

Procgen Messias speaking the gospel

@jagsdesign Год назад

this one is quite cool and any more examples of use case videos will be super useful and appreciated. Do you have any links where we can see more of your work

@PaulMerrellResearch Год назад

Thanks, I have some more information on my website: paulmerrell.org/ And I have another RU-vid Channel: ru-vid.com/show-UCdrIZ0-6i0xl31L63hhETdQ I hope to make some more videos soon.

@johnnydalvi3978 2 года назад

Love your work man, congratulations and thanks for sharing. For the problem in the last algorithm explained, can't you snap the approximated boolean and the minkowski sum to a pseudo grid? If you treat space as discrete positions instead of continuous, Perhaps it could collapse the small possible differences that were created

@ItsJustAstronomical 2 года назад

Thanks, that's a good suggestion. I did look into approximating it on a grid, but I couldn't get it to make all the shapes I wanted it to make. There may be a way to do it this way, but I had a lot of trouble with it.

@johnnydalvi3978 2 года назад

@@ItsJustAstronomical I see, yeah, it's quite a complex problem to solve. I'm excited to see what you're going to come up with next btw. Again, thanks for sharing this, I love procgen and I'll surely use it in the future.

@slvrcross Год назад

Okay do Fibonacci Sequence + Aperiodic monotiles next lol

@senhorengenheiro 7 месяцев назад

hum... i have to code a bit and test, but i think this has some application to my problem...

@PaulMerrellResearch 7 месяцев назад

Happy to hear that! Now I'm curious what you're working on.

@senhorengenheiro 7 месяцев назад

@@PaulMerrellResearch Its earth science modelling. The simple case seems pretty similar to multipoint simulations in geostatistics, but the continuous case is very interesting. Now getting time to experiment is the difficult part. Since I've left academia time is scarce for new stuff.

@DC9V 2 года назад

Hi Paul, I think there's a mismatch in the quality of your content and the quality of your videos in terms of resolution. Have you considered upgrading to 1440p or higher? I'm watching at 4K desktop resolution, using studio headphones. In my opinion, 720p does not provide a pleasing audio quality. It sounds fuzzy and grainy. I would also like to recommend an additional pop filter for your microphone.