Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

This is a fun interactive article explaining the intuition behind Gaussian Processes. Gaussian Processes allow you to construct a distribution over functions with a continuous domain. They are incredibly useful for applications like Bayesian regression.

alec_helbling's profile picture

Alec Helbling

10,728 subscribers

41,360 Aufrufe • vor 1 Jahr •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Flow Matching aims to learn a "flow" that transforms a simple source distribution (e.g. Gaussian) to an arbitrarily complex target distribution. This video shows the evolution of the marginal probability path as a source distribution is transformed to a target distribution.
0:13

Flow Matching aims to learn a "flow" that transforms a simple source distribution (e.g. Gaussian) to an arbitrarily complex target distribution. This video shows the evolution of the marginal probability path as a source distribution is transformed to a target distribution.

Alec Helbling

150,399 Aufrufe • vor 1 Jahr

One of the simplest algorithms for sampling from a probability distribution is Random Walk Metropolis-Hastings. It proposes new samples by taking Gaussian-distributed steps, accepting or rejecting them to maintain the target distribution. I call this pdf the "fidget spinner".
0:15

One of the simplest algorithms for sampling from a probability distribution is Random Walk Metropolis-Hastings. It proposes new samples by taking Gaussian-distributed steps, accepting or rejecting them to maintain the target distribution. I call this pdf the "fidget spinner".

Alec Helbling

79,869 Aufrufe • vor 1 Jahr

This new Spline feature (importing Gaussian Splatting) and portal card effect is a perfect match! You should try it!!
0:15

This new Spline feature (importing Gaussian Splatting) and portal card effect is a perfect match! You should try it!!

Max

356,866 Aufrufe • vor 2 Jahren

Apple just trained a 3D Gaussian head reconstruction model on 10,000+ subjects. Feed-forward. No test-time optimization. New identity in, reconstructed Gaussian head out. The UV-parameterized Gaussian representation decouples the number of Gaussians from the number and resolution of input images, making it practical to train with many high resolution views. And the heads are not just static either: text-conditioned identity generation, plus blendshape-driven latent animation across identities. We've been building in the 3D Gaussian Splatting space for a while. The gap between "research demo" and "works on real people at scale" is closing fast.
0:12

Apple just trained a 3D Gaussian head reconstruction model on 10,000+ subjects. Feed-forward. No test-time optimization. New identity in, reconstructed Gaussian head out. The UV-parameterized Gaussian representation decouples the number of Gaussians from the number and resolution of input images, making it practical to train with many high resolution views. And the heads are not just static either: text-conditioned identity generation, plus blendshape-driven latent animation across identities. We've been building in the 3D Gaussian Splatting space for a while. The gap between "research demo" and "works on real people at scale" is closing fast.

KIRI Engine - 3D Scanner App

11,903 Aufrufe • vor 19 Tagen

Gaussian splat of a fire bug.
0:15

Gaussian splat of a fire bug.

Dany Bittel

86,686 Aufrufe • vor 8 Monaten

Trippy to explore a 4D Gaussian Splatting scene in Blender #b3d
0:13

Trippy to explore a 4D Gaussian Splatting scene in Blender #b3d

Alex Martinelli

46,605 Aufrufe • vor 5 Monaten

Testing InstantSplat with a few frames from Oppenheimer, super fast 3D Gaussian Splatting
0:12

Testing InstantSplat with a few frames from Oppenheimer, super fast 3D Gaussian Splatting

Radamés Ajna

48,864 Aufrufe • vor 2 Jahren

I wrote this fun interactive article explaining Isomap, a classic non-linear dimensionality reduction technique. Isomap captures the local similarity structure of data through a graph and computes an embedding that preserves this structure. Check it out! Link below.
0:18

I wrote this fun interactive article explaining Isomap, a classic non-linear dimensionality reduction technique. Isomap captures the local similarity structure of data through a graph and computes an embedding that preserves this structure. Check it out! Link below.

Alec Helbling

41,045 Aufrufe • vor 6 Monaten

I made a 3D Gaussian Splatting renderer for WebGL! The following scene renders 1.3M splats in real time. I wanted to understand a bit more how gaussian splats were rasterized, reimplementing the original paper seemed to be the best approach. I will publish it on github soon!
0:17

I made a 3D Gaussian Splatting renderer for WebGL! The following scene renders 1.3M splats in real time. I wanted to understand a bit more how gaussian splats were rasterized, reimplementing the original paper seemed to be the best approach. I will publish it on github soon!

kishimisu

84,532 Aufrufe • vor 2 Jahren

3DGS render blender add-on v3.0 ( was just open-sourced! With KIRI tools, you can use "3DGS to mesh" function to get a mesh from Gaussian splatting, and now you can convert the mesh back to Gaussian splatting. It's kind of ironic, but we just try to bring handy tools to everyone. #GaussianSplatting #Blender
0:13

3DGS render blender add-on v3.0 ( was just open-sourced! With KIRI tools, you can use "3DGS to mesh" function to get a mesh from Gaussian splatting, and now you can convert the mesh back to Gaussian splatting. It's kind of ironic, but we just try to bring handy tools to everyone. #GaussianSplatting #Blender

Chris make some 3D scans

39,221 Aufrufe • vor 1 Jahr

Ask Claude to document and describe the main flows in your app and output in a single page html + json data file. Incredibly useful for humans and the JSON file is very useful for explaining the flow to the LLM when working on new features/bugfixes.
0:18

Ask Claude to document and describe the main flows in your app and output in a single page html + json data file. Incredibly useful for humans and the JSON file is very useful for explaining the flow to the LLM when working on new features/bugfixes.

Dave Jeffery

482,937 Aufrufe • vor 29 Tagen

1 of N reasons why sharding is a great way to scale a database? Backup speed. This is one of the fun little animations I worked on in my recent interactive sharding article. In case you missed it, link below.
0:12

1 of N reasons why sharding is a great way to scale a database? Backup speed. This is one of the fun little animations I worked on in my recent interactive sharding article. In case you missed it, link below.

Ben Dicken

13,157 Aufrufe • vor 1 Jahr

gaussian splat of a honeybee See it in 3D:
0:12

gaussian splat of a honeybee See it in 3D:

Dany Bittel

1,510,429 Aufrufe • vor 8 Monaten

I've been putting together an interactive tool called DiffusionLab for explaining the geometric intuition behind diffusion and flow based generative models. Sampling is actually being done in the browser using Tensorflow.js! It is still in the very early stages.
0:11

I've been putting together an interactive tool called DiffusionLab for explaining the geometric intuition behind diffusion and flow based generative models. Sampling is actually being done in the browser using Tensorflow.js! It is still in the very early stages.

Alec Helbling

104,626 Aufrufe • vor 1 Jahr

The Gaussian Integral. [
0:19

The Gaussian Integral. [

Abakcus

146,948 Aufrufe • vor 4 Monaten

You can capture reality with remarkable fidelity - here’s a 1:1 3d gaussian splat perfectly aligned with reality. Once Meta layers in a scalable version of their codec avatar tech - this stuff is about to get trippy. Literally transcending time & space.
0:10

You can capture reality with remarkable fidelity - here’s a 1:1 3d gaussian splat perfectly aligned with reality. Once Meta layers in a scalable version of their codec avatar tech - this stuff is about to get trippy. Literally transcending time & space.

Bilawal Sidhu

106,690 Aufrufe • vor 7 Monaten

Wrote a (quite long) article for Codrops with a demo made in #webgpu. Hope it gets to be useful for anyone
0:17

Wrote a (quite long) article for Codrops with a demo made in #webgpu. Hope it gets to be useful for anyone

Hat

40,478 Aufrufe • vor 1 Jahr

Gaussian splatting is getting crazy!
0:13

Gaussian splatting is getting crazy!

Christopher Fryant

46,970 Aufrufe • vor 7 Monaten

splaTV, developed by Kevin Kwok, is a browser-based implementation for experiencing dynamic Gaussian Splatting with Spacetime Gaussians. This newly released application supports both WebGL and WebXR technologies and is available under the MIT License. 🔗
0:10

splaTV, developed by Kevin Kwok, is a browser-based implementation for experiencing dynamic Gaussian Splatting with Spacetime Gaussians. This newly released application supports both WebGL and WebXR technologies and is available under the MIT License. 🔗

Radiance Fields

18,659 Aufrufe • vor 2 Jahren

Imagine asking for a drink but they hit you with a domain expansion 😭
0:14

Imagine asking for a drink but they hit you with a domain expansion 😭

vids that go hard

3,220,335 Aufrufe • vor 2 Jahren