Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

My new favorite easy-to-use interactive 3D visualization library is Plotly! Here is a visualization of the CIFAR dataset where images are first projected into 2,048-dimensional hidden vectors using InceptionV3 and then reduced to 3D using UMAP.

Xavier Bresson

17,442 subscribers

56,508 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

Lionel2 years ago

Looks way smoother than matplotlib 3d figures. How many observations are in this 3d scatter? Does it ever get slow?

Xavier Bresson2 years ago

50,000 data points. never slow, very smooth on my laptop.

Plotly2 years ago

Amazing! Thanks for sharing @xbresson 🙌

Srivathsan Srinivas2 years ago

I am going to try it. Been wanting to plot graphs and interact with. Thanks @xbresson for this post!

Eamon McAndrew2 years ago

Do you have the code for this specific implementation. The 3D Umap cords to interactive plot like this ?

Xavier Bresson2 years ago

will share code soon

KC Archtux | LEC CHAMPION 💙2 years ago

looks so great thx

Jochem Gietema2 years ago

I can see if I can support 3D plots in (also based on Plotly), then you can directly see the actual images as well.

Nur2 years ago

For 3D visualization, should data have only 3 variables? Or how many variables can I use for this visualization?

Stephen Harrington2 years ago

Combine Plotly with dash for more controls and components.

Related Videos

A drone scan of the partial glacier collapse in Blatten, reconstructed using 3D Gaussian Splatting. New approaches to disaster visualization can provide a rapid overview of the situation.

A drone scan of the partial glacier collapse in Blatten, reconstructed using 3D Gaussian Splatting. New approaches to disaster visualization can provide a rapid overview of the situation.

MrNeRF

24,208 views • 1 year ago

An interactive 3D simulation and visualization of a black hole, leveraging Three.js for rendering and custom GLSL shaders to achieve stunning details in the event horizon, starfield, and accretion disk. Coded using newly released Grok 4 from xAI

An interactive 3D simulation and visualization of a black hole, leveraging Three.js for rendering and custom GLSL shaders to achieve stunning details in the event horizon, starfield, and accretion disk. Coded using newly released Grok 4 from xAI

Techartist

2,987,901 views • 1 year ago

The GBU-39 – a visual guide to Israel’s “weapon of choice” in Gaza. This is the first in a series of articles using interactive 3D models alongside images from the OSMP archive to help researchers understand and identify widely-used munitions 1/10

The GBU-39 – a visual guide to Israel’s “weapon of choice” in Gaza. This is the first in a series of articles using interactive 3D models alongside images from the OSMP archive to help researchers understand and identify widely-used munitions 1/10

Open Source Munitions Portal

67,522 views • 1 year ago

I'm creating 3D tours of open single cell RNA-seq data in UMAP space. Here, using data from 50k brain cells by the allen institute . ( The UMAP position and class of every cell is read into Blender, realized as a stylized, class-specific model I sculpted

I'm creating 3D tours of open single cell RNA-seq data in UMAP space. Here, using data from 50k brain cells by the allen institute . ( The UMAP position and class of every cell is read into Blender, realized as a stylized, class-specific model I sculpted

Brad Krajina

48,138 views • 3 years ago

New Hytale Footage... Kind of.. Well. Nerd Video!!! I was asked to show how our Github looks like using "Gource" visualization. Here it is.. I wonder if you can see the part where collapsed the 300 branches into a single new main branch. Enjoy ;)

New Hytale Footage... Kind of.. Well. Nerd Video!!! I was asked to show how our Github looks like using "Gource" visualization. Here it is.. I wonder if you can see the part where collapsed the 300 branches into a single new main branch. Enjoy ;)

Slikey

241,126 views • 7 months ago

I created a 3D Gaussian Splat of my kitchen using 1/3rd the images it used to take me by using NVIDIA AI Developer's 3DGRUT! I can now use 180 degree fisheye images and ray tracing to make detailed splats. The only reason the scene isn't sharper is because my input images weren't super sharp - when I took the images back in October, I was still learning to use the lens. I plan to make a "first reactions/overview video". Tutorial after that. For reference, this took 206 images and the ultrawide on my iPhone took 608 images to capture. #3D #AEC #Computervision

I created a 3D Gaussian Splat of my kitchen using 1/3rd the images it used to take me by using NVIDIA AI Developer's 3DGRUT! I can now use 180 degree fisheye images and ray tracing to make detailed splats. The only reason the scene isn't sharper is because my input images weren't super sharp - when I took the images back in October, I was still learning to use the lens. I plan to make a "first reactions/overview video". Tutorial after that. For reference, this took 206 images and the ultrawide on my iPhone took 608 images to capture. #3D #AEC #Computervision

Jonathan Stephens

30,663 views • 1 year ago

A test of real-time transfer of images captured on Quest to a PC, where they are converted into 3D using Apple's SHARP. Currently, the final 3DGS output is displayed on the PC. The next step is to bring the result back into Quest for in-headset viewing. #3DGS #metaquest #AR

A test of real-time transfer of images captured on Quest to a PC, where they are converted into 3D using Apple's SHARP. Currently, the final 3DGS output is displayed on the PC. The next step is to bring the result back into Quest for in-headset viewing. #3DGS #metaquest #AR

Takashi Yoshinaga

11,575 views • 3 months ago

EVoC is a library designed specifically for fast clustering of high dimensional embedding vectors. It can produce high quality clusters extremely efficiently, and requires little to no hyperparameter tuning. Better clustering than UMAP + HDBSCAN; faster clustering than KMeans.

EVoC is a library designed specifically for fast clustering of high dimensional embedding vectors. It can produce high quality clusters extremely efficiently, and requires little to no hyperparameter tuning. Better clustering than UMAP + HDBSCAN; faster clustering than KMeans.

Leland McInnes

26,121 views • 3 months ago

3D for Hana is here. The first canvas that combines 3D and 2D in real-time. Convert any shape to a 3D model in a non-destructive process. All systems (vectors, booleans, layouts, events, etc.) work together.

3D for Hana is here. The first canvas that combines 3D and 2D in real-time. Convert any shape to a 3D model in a non-destructive process. All systems (vectors, booleans, layouts, events, etc.) work together.

Spline

114,540 views • 7 months ago

Select your cell: I'm prototyping an interactive sc RNA-seq portal where the UMAP is dynamically linked to morphing 3D artistic renders of each cell type. You can play with the initial build below.

Select your cell: I'm prototyping an interactive sc RNA-seq portal where the UMAP is dynamically linked to morphing 3D artistic renders of each cell type. You can play with the initial build below.

Brad Krajina

51,243 views • 10 months ago

wow.. text to 3D would AI is here you can generate 3D assets using text/image and build up a 3D world.. and even auto rig characters. link in comment

wow.. text to 3D would AI is here you can generate 3D assets using text/image and build up a 3D world.. and even auto rig characters. link in comment

el.cine

212,681 views • 1 year ago

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

Amira Zairi

186,621 views • 3 months ago

Big announcement🚀 Our comprehensive course on 3D Animated Character Creation using Blender 3D is officially online. If you're new to the 3D world and keen on crafting your very first animated character, this is for you. #B3d #animation #CGI #Blender3D

Big announcement🚀 Our comprehensive course on 3D Animated Character Creation using Blender 3D is officially online. If you're new to the 3D world and keen on crafting your very first animated character, this is for you. #B3d #animation #CGI #Blender3D

Ram Singh

36,246 views • 2 years ago

More experiments of this workflow: Generating quick 3d models using Lumas Genie 3D. A text prompt generates 4 models in 10 seconds. Then, using Lumas webviewer, I feed a screencapture of the model into Krea ai which details the model based on another prompt. Finally, Magnific AI is used to add the final finish. The Santa mechs are insanely refined😱 Check out the final "Renders" below. #3d #ai

More experiments of this workflow: Generating quick 3d models using Lumas Genie 3D. A text prompt generates 4 models in 10 seconds. Then, using Lumas webviewer, I feed a screencapture of the model into Krea ai which details the model based on another prompt. Finally, Magnific AI is used to add the final finish. The Santa mechs are insanely refined😱 Check out the final "Renders" below. #3d #ai

Martin Nebelong

88,080 views • 2 years ago

After two weeks of coding, preview of my new tool to visualize the folding pathways of an #RNA during its transcription. Pathways are computed with my new #rustlang algorithm. Visualization and GUI are made with #kotlin, #javafx and my rnartistcore library. #bioinformatics

After two weeks of coding, preview of my new tool to visualize the folding pathways of an #RNA during its transcription. Pathways are computed with my new #rustlang algorithm. Visualization and GUI are made with #kotlin, #javafx and my rnartistcore library. #bioinformatics

RNArtist

70,312 views • 3 years ago

We built a web app that lets you fly a spaceship through a 3D constellation of music - powered by our Lyria RealTime model. 🎶 Space DJ is an interactive visualization where every star represents a different music genre. As you explore, your path is translated into prompts for the API, creating a continuously evolving soundtrack. ↓

We built a web app that lets you fly a spaceship through a 3D constellation of music - powered by our Lyria RealTime model. 🎶 Space DJ is an interactive visualization where every star represents a different music genre. As you explore, your path is translated into prompts for the API, creating a continuously evolving soundtrack. ↓

Google DeepMind

280,305 views • 8 months ago

Been pushing Rive's new 3D and shader support to see what's possible 🚀 Using AI + scripting, I was able to: • Import 3D models • Generate cameras and lights • Create custom shaders (wireframe, AO, sketch, toon) • Build materials • Project animated textures onto 3D geometry • Place 2D components directly in 3D space It's pretty wild to see how quickly Rive is evolving into a true all-in-one platform for interactive design.

Been pushing Rive's new 3D and shader support to see what's possible 🚀 Using AI + scripting, I was able to: • Import 3D models • Generate cameras and lights • Create custom shaders (wireframe, AO, sketch, toon) • Build materials • Project animated textures onto 3D geometry • Place 2D components directly in 3D space It's pretty wild to see how quickly Rive is evolving into a true all-in-one platform for interactive design.

Sanu Sagar

18,218 views • 1 month ago

Here is a 3D visualization of the coming solar storm using model parameters from NASA's run, NOAA's run (shown below), and the coronagraph views from STEREO-A/COR2 and SOHO/LASCO. The storm is expected to hit Earth early December 9. The 3D visualization clearly shows the low inclination orientation of the solar slinky core inside the larger storm envelope. Of course, the earlier eruption that erupted to the northeast, might deflect this structure a little bit, but likely that will only make the structure move more towards the ecliptic plane, which will give us a larger chance of crossing through the solar slinky core. One nice thing about low inclination flux rope cores is that they almost ALWAYS have southward field in them at some point. So this is good news for aurora photographers-- as long as this solar storm stays true to its launch trajectory and inclination, we could see some organized southward pointed magnetic field. Considering this solar storm is fast-- that usually indicates the storm will not deviate much from its original launch trajectory! Here is the link to a static frame of the 3D frame visualization so you can fly around it yourself:

Here is a 3D visualization of the coming solar storm using model parameters from NASA's run, NOAA's run (shown below), and the coronagraph views from STEREO-A/COR2 and SOHO/LASCO. The storm is expected to hit Earth early December 9. The 3D visualization clearly shows the low inclination orientation of the solar slinky core inside the larger storm envelope. Of course, the earlier eruption that erupted to the northeast, might deflect this structure a little bit, but likely that will only make the structure move more towards the ecliptic plane, which will give us a larger chance of crossing through the solar slinky core. One nice thing about low inclination flux rope cores is that they almost ALWAYS have southward field in them at some point. So this is good news for aurora photographers-- as long as this solar storm stays true to its launch trajectory and inclination, we could see some organized southward pointed magnetic field. Considering this solar storm is fast-- that usually indicates the storm will not deviate much from its original launch trajectory! Here is the link to a static frame of the 3D frame visualization so you can fly around it yourself:

Dr. Tamitha Skov

18,461 views • 7 months ago