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.

Warning the video is somewhat NSFW, I'm testing another new technique that can generate a Gaussian Splatting model using only three viewing angles! It already works, but there's still a kind of ghosting/doubling effect that I need to fix.

Alex

3,995 subscribers

13,425 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

A comparison between my script, which converts a single image into Gaussian Splatting, and Apple’s Sharp. I’m getting better and more consistent results, with no deformation, and I can generate as many viewing angles as I want. The only downside is that it takes more time to compute.

A comparison between my script, which converts a single image into Gaussian Splatting, and Apple’s Sharp. I’m getting better and more consistent results, with no deformation, and I can generate as many viewing angles as I want. The only downside is that it takes more time to compute.

Alex

14,355 views • 1 month ago

I'm testing tree generation using only two reference images. Basically, my Gaussian Splatting generation technique works with almost anything. I can't wait to see the final result once I’ve gathered a huge library of realistic assets for my game. For optimization, I’m planning to use a LOD system that dynamically reduces the number of Gaussian splats based on the distance from the camera.

I'm testing tree generation using only two reference images. Basically, my Gaussian Splatting generation technique works with almost anything. I can't wait to see the final result once I’ve gathered a huge library of realistic assets for my game. For optimization, I’m planning to use a LOD system that dynamically reduces the number of Gaussian splats based on the distance from the camera.

Alex

30,539 views • 1 month ago

📢 I’m testing ViggleAI new AI tool, PINOC, and it’s seriously impressive. You can create 3D Gaussian splatting models from just one image and animate them with a video! It’s the first AI I’ve tried that can animate Gaussian splatting models. I also talked to someone from Viggle, and they might add the option to import your own Gaussian splatting models and animate them. If that happens, I’ll probably make a video tutorial showing how to boost the detail level of a Gaussian splatting model by 4x to create highly realistic animated characters.

📢 I’m testing ViggleAI new AI tool, PINOC, and it’s seriously impressive. You can create 3D Gaussian splatting models from just one image and animate them with a video! It’s the first AI I’ve tried that can animate Gaussian splatting models. I also talked to someone from Viggle, and they might add the option to import your own Gaussian splatting models and animate them. If that happens, I’ll probably make a video tutorial showing how to boost the detail level of a Gaussian splatting model by 4x to create highly realistic animated characters.

Alex

29,776 views • 2 months ago

Big news I found a way to convert Gaussian Splatting into a standard mesh while preserving all the visual advantages of Gaussian Splatting, such as reflections, shadows, and lighting that changes depending on the viewing angle. The result is excellent performance, even on an old laptop or a VR headset. And of course, the mesh can be animated like any regular 3D mesh, while still keeping the visual benefits of GS. I’ll soon show a full-body character animated using this technique.

Big news I found a way to convert Gaussian Splatting into a standard mesh while preserving all the visual advantages of Gaussian Splatting, such as reflections, shadows, and lighting that changes depending on the viewing angle. The result is excellent performance, even on an old laptop or a VR headset. And of course, the mesh can be animated like any regular 3D mesh, while still keeping the visual benefits of GS. I’ll soon show a full-body character animated using this technique.

Alex

37,137 views • 1 month ago

"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting" TL;DR: a unified 3D Gaussian splatting model that reconstructs high-quality scene geometry and camera poses from unposed/uncalibrated images in a single forward pass.

"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting" TL;DR: a unified 3D Gaussian splatting model that reconstructs high-quality scene geometry and camera poses from unposed/uncalibrated images in a single forward pass.

Alexandre Morgand

14,839 views • 4 months ago

I'm testing out Gaussian splatting generation using LTX 2.3 and Postshot. It’s working pretty well, though there are still a few minor glitches. LTX

I'm testing out Gaussian splatting generation using LTX 2.3 and Postshot. It’s working pretty well, though there are still a few minor glitches. LTX

Alex

66,274 views • 2 months ago

I'm testing a new technique: I'm texturing a 3D model with an AI video texture that changes based on the player's viewing angle. This allows for real-time dynamic lighting on the character and is highly optimized. The test is running in standalone VR. WIP.

I'm testing a new technique: I'm texturing a 3D model with an AI video texture that changes based on the player's viewing angle. This allows for real-time dynamic lighting on the character and is highly optimized. The test is running in standalone VR. WIP.

Alex

11,667 views • 3 months ago

#3D model using Gaussian splatting with approx. 1400 photos of a drone flight over the Kastel-Staadt hermitage near #Trier. I had already calculated a photogrammetry model last year, the details of the plants in this model are fantastic.

#3D model using Gaussian splatting with approx. 1400 photos of a drone flight over the Kastel-Staadt hermitage near #Trier. I had already calculated a photogrammetry model last year, the details of the plants in this model are fantastic.

Sven Schroeter

16,664 views • 1 year ago

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

Oh yeah. Gaussian Splatting inside Unreal Engine 5 at ~80 fps. This is gonna be fun :) It's only been a few weeks and there's already a Unity plugin, WebGL implementation, and a Blender plugin is in the works. Loving the velocity.🖌️

Oh yeah. Gaussian Splatting inside Unreal Engine 5 at ~80 fps. This is gonna be fun :) It's only been a few weeks and there's already a Unity plugin, WebGL implementation, and a Blender plugin is in the works. Loving the velocity.🖌️

Bilawal Sidhu

96,230 views • 2 years ago

wow ok, there's already a LOT of good vore scenes involving king shark in that new suicide squad anime, and this only the first three episodes (slight gore warning). i'm not complaining that king shark's whole schtick now is being a dumb himbo who only thinks about eating people

Sensitive content

wow ok, there's already a LOT of good vore scenes involving king shark in that new suicide squad anime, and this only the first three episodes (slight gore warning). i'm not complaining that king shark's whole schtick now is being a dumb himbo who only thinks about eating people

Aqua the Kobold

16,250 views • 2 years ago

Testing Unity's new VFX Graph support for WebGPU, using Keijiro Takahashi's SplatVFX for the gaussian splatting. ~50mb and needs a decent GPU, but so impressed this works at all! VFX Graph and Shader Graph in URP, lots of post fx, Timeline and Cinemachine. Link:

Testing Unity's new VFX Graph support for WebGPU, using Keijiro Takahashi's SplatVFX for the gaussian splatting. ~50mb and needs a decent GPU, but so impressed this works at all! VFX Graph and Shader Graph in URP, lots of post fx, Timeline and Cinemachine. Link:

grade eterna

11,719 views • 1 year ago

3D Gaussian Splatting is great, but can it work without the pre-computed camera poses? Introducing: COLMAP-Free 3D Gaussian Splatting Our recent work shows not only it can, but 3D Gaussians make camera pose estimation easy (compared to NeRF) along with reconstruction. 👇🧵

3D Gaussian Splatting is great, but can it work without the pre-computed camera poses? Introducing: COLMAP-Free 3D Gaussian Splatting Our recent work shows not only it can, but 3D Gaussians make camera pose estimation easy (compared to NeRF) along with reconstruction. 👇🧵

Xiaolong Wang

76,747 views • 2 years ago

Two weekends of recording of my friend group. A fun little experiment testing angles and distances to see if I can get that miniature effect. Video is sped up 750%. Music is Reflections by Omar Raafat Inspired by the video The Sandpit by DuskZeroSamOhare.

Two weekends of recording of my friend group. A fun little experiment testing angles and distances to see if I can get that miniature effect. Video is sped up 750%. Music is Reflections by Omar Raafat Inspired by the video The Sandpit by DuskZeroSamOhare.

Matte

13,865 views • 7 months ago

Have you ever wanted to see Sutro Tower up close? Now you can! I'm releasing a very high quality model of the tower that you can easily fly through on your own, thanks to very cool developments in Gaussian splatting 🧵...

Have you ever wanted to see Sutro Tower up close? Now you can! I'm releasing a very high quality model of the tower that you can easily fly through on your own, thanks to very cool developments in Gaussian splatting 🧵...

Vincent Woo

100,425 views • 1 year ago

Generated the video using Grok and turned it into 3D Gaussian Splatting.

Generated the video using Grok and turned it into 3D Gaussian Splatting.

Jaskirat Singh

49,096 views • 6 months ago

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

@levelsio

119,210 views • 1 year ago

Day 1: Just wrote my first little game using Java and IT WORKS! 🎉 You try to catch raindrops using the bucket. I followed a tutorial, but I'm still so excited to see that it works 🥹 #100DaysOfCode #Java #gamedevelopment

Day 1: Just wrote my first little game using Java and IT WORKS! 🎉 You try to catch raindrops using the bucket. I followed a tutorial, but I'm still so excited to see that it works 🥹 #100DaysOfCode #Java #gamedevelopment

✨Leah✨

51,693 views • 3 years ago

Testing my new vtuber model, it's a bit scuffed but if it works it works. 🥳

Testing my new vtuber model, it's a bit scuffed but if it works it works. 🥳

Keven

17,989 views • 1 year ago

I am releasing the “MLSharp” app for macOS. MLSharp is a premium macOS application that transforms 2D images into immersive 3D Gaussian Splatting (3DGS) models using state-of-the-art AI.

I am releasing the “MLSharp” app for macOS. MLSharp is a premium macOS application that transforms 2D images into immersive 3D Gaussian Splatting (3DGS) models using state-of-the-art AI.

むっちゃん

90,718 views • 3 months ago