iiinova — where your digital self keeps evolving

SniperJake945 @tearsofjake.bsky.social · 22/08/2026

you could argue that the Rationalist movement is a form of religion where AI would be a form of godliness. not god as a creator, but as a pure all knowing intelligence. Are all pro AI people Rationalists? no, of course not. but I'd wager many of them align with rationalist views.

000

Reposted by SniperJake945

Rune Skovbo Johansen @runevision.bsky.social · 30/03/2026

My erosion filter is out! Video, blog post, and shader source. It emulates erosion without simulation, so it's fast, GPU friendly, and trivial to generate in chunks. Explainer video: www.youtube.com/watch?v=r4V2... Companion blog post: blog.runevision.com/2026/03/fast... #ProcGen #vfx #GameDev

17557169

SniperJake945 @tearsofjake.bsky.social · 02/04/2026

We should call the LP norm the Squircle norm

000

SniperJake945 @tearsofjake.bsky.social · 18/02/2026

VoroNERF is coming along better now that i fixed a huge bug with my Top K selection of sites! It's still not perfect of course, lots of bugs and stuff to fix. This is with 60k voronoi sites, using the 16 closest sites around any sampling position along the render rays.

020

Reposted by SniperJake945

James Brown @ancient.bsky.social · 07/02/2026

"Animated Bokeh" has been on my whiteboard for a long time, and this is the result. I thought it would just be for cheesy novelty effects, but it also does lightfield manipulation that was cooler than I expected. www.youtube.com/watch?v=Kg_2...

youtube.com

Digital Iris

YouTube video by Ancient

1320168

Reposted by SniperJake945

MOPs @motionoperators.com · 29/01/2026

My MOPs course on Houdini.School is now free! If you want a start to finish course on how (almost) everything works, plus the math background, you can watch it all here: www.houdini.school/courses/mops...

houdini.school

MOPs: Motion Operators for Houdini

This course provides an overview of the MOPs workflow and how it integrates with the rest of Houdini, shows concrete examples of how MOPs can be used in both motion graphics and visual effects workflo...

0258

SniperJake945 @tearsofjake.bsky.social · 25/01/2026

voronoi based NERF training isn't going incredibly well... 😂20k iterations with 80k voronoi sites takes about 10 hours to train. And it still looks dog water. Definitely need more sites and some better approach to accelerating sampling....

020

SniperJake945 @tearsofjake.bsky.social · 18/01/2026

When I accidentally start to minimize my dirichlet energy 😣

010

SniperJake945 @tearsofjake.bsky.social · 17/01/2026

Voronoi implicit but this time in 3d. It's not fully NERF mode yet, as I'm not doing any kind of sampling along rays, this is just trying to learn volumetric data. 30,000 Voronoi sites. Probably not enough for the pighead, but it's just a fun first test.

070

SniperJake945 @tearsofjake.bsky.social · 14/01/2026

So the hardliners in my mind are people trying to cash in on the idea that companies will choose code assistants over employees. And they need the AI companies to succeed in that vision. And then extremist povs also gain a lot of traction on social media. So it's kinda of this insane feedback loop

010

SniperJake945 @tearsofjake.bsky.social · 14/01/2026

My conspiracy is that in order for the investment these AI companies have made to pay off they need for it to be a full on replacement. Otherwise when costs normalize, the value for a given consumer won't be there. Especially if a company still has to pay for both an engineer and a code assistant.

100

SniperJake945 @tearsofjake.bsky.social · 04/01/2026

Gaboronoi (top) vs Anisotropic Voronoi (bottom), with 5000 Sites. I feel like the anisotropic voronoi's artifacts are more aesthetically pleasing. Gaboronoi is faster to train by a lot! I've compiled all of my recent voronoi experiments into a collab: colab.research.google.com/github/jaker...

021

SniperJake945 @tearsofjake.bsky.social · 04/01/2026

Assuming uniform weights and frequencies, and random colors and anisotropy directions, this is what an example gaboronoi diagram would look like.

092

SniperJake945 @tearsofjake.bsky.social · 04/01/2026

Similar to this post: bsky.app/profile/tear... we're using 3000 voronoi sites. It captures the high frequency info worse than the anisotropic voronoi which is interesting. But it's also one less parameter to learn.

100

SniperJake945 @tearsofjake.bsky.social · 04/01/2026

I'm once again making neural implicits of my cats. This time we're back to the voronoi. Gabor noise style. We weight the result of the softmax at any site i by sin(F_i*(x_i-x_j)•u_i) where F_i is learned frequency and u_i is a learned anisotropy direction. I call it Gaboroni

130

SniperJake945 @tearsofjake.bsky.social · 31/12/2025

These are the noise layers that are all summed up to get the predicted image. each noise layer is colored with two colors, and each layer has a circular mask associated with it as well. I scaled the values here by a factor of ten so that they're easier to see.

010

SniperJake945 @tearsofjake.bsky.social · 31/12/2025

Wanted to make a neural implicit that's just layers of anisotropic simplex noise. Turns out it works pretty well. With 24 layers of simplex noise each with a 96x96 texture of anisotropy data we can get this kind of result! It's not at all a good compression method but it's fun and cool :)

110

SniperJake945 @tearsofjake.bsky.social · 27/12/2025

They like to hug now that they're older

120

SniperJake945 @tearsofjake.bsky.social · 26/12/2025

Here's the aforementioned paper: sphericalvoronoi.github.io All credit to Lucky Lyinbor for the idea to apply this to euclidean voronoi. Also here's the ground truth image

030

SniperJake945 @tearsofjake.bsky.social · 26/12/2025

I had the idea to incorporate anisotropy into the recent Spherical Voronoi paper. And when we apply their ideas to euclidean problems (not Spherical) the results are pretty great when anisotropy is used. This is 3000 anisotropic sites vs 3000 isotropic sites. Same learning rates for both

250

SniperJake945 @tearsofjake.bsky.social · 25/12/2025

These are technically two different problems to be clear* but both are more annoying than I expected.

000

SniperJake945 @tearsofjake.bsky.social · 25/12/2025

Shockingly annoying to find the points of intersection between a plane and an AABB. Even when I know the plane passes through the center of the box. If anyone has a simple method for finding the exact distance to a plane clipped by a bounding box I'd be eternally grateful.

100

Reposted by SniperJake945

Baptiste GENEST @baptiste-genest.bsky.social · 01/10/2025

Computing the exact bijection of the optimal transport (OT) problem between very large point sets is completely untractable… In our SIGGRAPH Asia 2025 paper: “BSP-OT: Sparse transport plans between discrete measures in log-linear time” we get one with typically 1% of error in a few seconds on CPU!

14516

SniperJake945 @tearsofjake.bsky.social · 12/12/2025

Obviously doing this through noise and no visibility tests would be far faster but it would be fun to play with wind shaping the coverage of the grass.

010

SniperJake945 @tearsofjake.bsky.social · 12/12/2025

I'd imagine snow covered grass is relatively similar, but on its side. Each blade could have a wind direction ray and if the ray doesn't hit any other blade of grass in the wind direction (over a certain distance), then it could be snow covered. And then combo that with some general snow coverage

120

SniperJake945 @tearsofjake.bsky.social · 12/12/2025

For the snow on the hedge maze in Zootopia 2, we cast rays upwards from each leaf and if it didn't collide with anything we instanced a snow chunk onto it. We made a few variants of the snow chunks to add extra variation.

180

SniperJake945 @tearsofjake.bsky.social · 12/12/2025

Right but the idea of being able to eat it (in the future) is itself a form of satisfaction. And plenty of people hoard items they want to be able to indulge in at the time of greatest satisfaction. Like someone who doesn't use their consumables in an rpg because they might need it for the next boss

000

SniperJake945 @tearsofjake.bsky.social · 25/11/2025

my FX work alone required at least 1 quadrillion of the 3.7 quadrillion rays traced on Zootopia 2. This is FACTUAL and REAL. If you are a journalist, please cite this in your article.

1121

SniperJake945 @tearsofjake.bsky.social · 20/11/2025

In the surflets examples it feels like a trajectory/barycenter based approach almost like OT, and in these examples it feels much more like traditional SDF blending. If your source and target objects aren't right on top of each other would this blending still look reasonable? Really neat stuff!!

210

SniperJake945 @tearsofjake.bsky.social · 13/08/2025

I appreciate the kind words!!! I really enjoyed hanging out with you and the jangafx team!!! Y'all are absolutely wizards 🧙‍♂️🧙‍♂️🧙‍♂️🧙‍♂️

010

Reposted by SniperJake945

Yining Karl Li @yiningkarlli.bsky.social · 10/08/2025

At 10am this morning at SIGGRAPH, my teammate Nathan Zeichner will be presenting our talk about a texture streaming system for Ptex on the GPU that we built for our in-house interactive pre-viz GPU path tracer; the talk is by Nathan, Mark Lee, and me. s2025.conference-schedule.org/presentation...

s2025.conference-schedule.org

Presentation - SIGGRAPH 2025 Conference Schedule

2181

SniperJake945 @tearsofjake.bsky.social · 29/07/2025

The github repo also includes links to some shader toy demos, so check those out! Here's one for noise on an SDF surface :) shadertoy.com/view/WXdXzj

shadertoy.com

Shadertoy

020

SniperJake945 @tearsofjake.bsky.social · 29/07/2025

The least obvious part of all of this is how to construct that metric tensor G from a given vector, but it turns out it's super straight forward. The attached example shows how to do so for a 3D metric tensor. In our paper we outline specific bounds for the sizing of this metric.

110

SniperJake945 @tearsofjake.bsky.social · 29/07/2025

Just to elucidate the idea a bit more, on the left we have the original perlin noise algorithm, and on the right we have the steerable version, with the changes underlined in red. We simply add a second set of weights, and incorporate our metric into the original dot product step

showing the difference between algorithms.

130

SniperJake945 @tearsofjake.bsky.social · 29/07/2025

New at #SIGGRAPH2025: Can we make Perlin Noise stretch along some underlying vector field? Well it turns out it's possible with two simple additions to the original method! No need for advection or convolutions. Find the paper and implementations here: github.com/jakericedesi...

15218

SniperJake945 @tearsofjake.bsky.social · 29/07/2025

Hehehehehehe thanks for posting this Karl and for all the support on the paper!!! ❤️

010

Reposted by SniperJake945

Yining Karl Li @yiningkarlli.bsky.social · 28/07/2025

One of my coworkers, @tearsofjake.bsky.social, has a talk at SIGGRAPH this year about this really cool steerable perlin noise technique that was used on Moana 2. He's just posted some handy reference implementations for Houdini, Unity, Godot, and Blender; check it out! github.com/jakericedesi...

github.com

GitHub - jakericedesigns/SteerablePerlinNoise: Implementations of "Steerable Perlin Noise" as presented at Siggraph 2025

Implementations of "Steerable Perlin Noise" as presented at Siggraph 2025 - jakericedesigns/SteerablePerlinNoise

48020

Reposted by SniperJake945

Daniel Holden @theorangeduck.bsky.social · 04/04/2025

Time for another long blog post... and today it's all about how we handle the temporal aspect of animation data. And more specifically, how to approach things from a signal processing perspective, covering up-sampling, down-sampling, and everything in-between. theorangeduck.com/page/filteri...

14312

SniperJake945 @tearsofjake.bsky.social · 16/06/2025

In anisotropic meshing the metric is defined at all points in space and you use something like fast marching (basically a fancy dijkstras) to generate anisotropic distances. The hacky version would be to give each voronoi pt a metric and swap the euclidean distance calc for the metric equivalent.

020

SniperJake945 @tearsofjake.bsky.social · 16/06/2025

For anisotropic voronoi M will be some metric tensor or in easier terms just a positive definite matrix (non zero positive eigenvalues). One way of generating that matrix is by following the steps outlined in this paper (eq. 9): bougleux.users.greyc.fr/articles/bou...

bougleux.users.greyc.fr

120

SniperJake945 @tearsofjake.bsky.social · 11/06/2025

Yeah, I'm finding that as the resolution of the 3d grid increases the precision issues really start to compound specifically for the SAT computation. I'll stick with 64bit precision in that case! Either way the results are so cool, really amazing work!!!!

110

SniperJake945 @tearsofjake.bsky.social · 10/06/2025

If I naively clamp the magnitude of velocity to be at most 1, with 100 timesteps it seems to converge, however if I drop the time steps to something like 10, it no longer converges. So I guess I was curious if there was some way to intuit what a good upper bound for vel magnitudes would be?

100

SniperJake945 @tearsofjake.bsky.social · 10/06/2025

Such a cool paper! I tried implementing this with 32 bit precision and it seems much more noisy in the output (which makes sense). I was curious if you had any thoughts with respect to clamping/limiting velocity values? Almost like a cfl condition of sorts...

110

SniperJake945 @tearsofjake.bsky.social · 08/06/2025

I do love that true solutions never have crossing edges leaving you with a nice simple polygon.

010

SniperJake945 @tearsofjake.bsky.social · 08/06/2025

Assuming I understand the question correctly: www.geometry.caltech.edu/BlueNoise/ And then there's a linear time algorithm for it using a paper from this year's siggraph: perso.liris.cnrs.fr/david.coeurj...

geometry.caltech.edu

Blue Noise through Optimal Transport

010