Loading video...

Video Failed to Load

Go Home

Mesh-2-Splat is merged into master, which allows converting meshes into splats in less than a second. I also made Fast-SAM3D run as a plugin. It makes it trivial to create new 3D GS assets from any image!

janusch_patas's profile picture

MrNeRF

16,830 subscribers

16,043 views • 6 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

every 3D mesh is kind of a compiled binary: printable, usable, but frozen. you can't just "make this hole 2mm wider" Cadena is just out to fix this, a decompiler of 3D meshes - converting it into an editable CAD program, step by step 🧊 app on spaces ▶️
0:13

every 3D mesh is kind of a compiled binary: printable, usable, but frozen. you can't just "make this hole 2mm wider" Cadena is just out to fix this, a decompiler of 3D meshes - converting it into an editable CAD program, step by step 🧊 app on spaces ▶️

Hugging Apps

30,165 views • 19 days ago

the fact that i can take an image of a room and turn it into a 3d model in one shot is actually insane this took like 30 seconds from image to 3d model
0:18

the fact that i can take an image of a room and turn it into a 3d model in one shot is actually insane this took like 30 seconds from image to 3d model

Jan

131,884 views • 9 months ago

As we move more and more into 3D, texturing 3D assets will be essential ☝️ Repainting 3D Assets is a new AI method that can take any 3D asset and paint it with a given text prompt. The results, while low-resolution, are pretty impressive.
0:18

As we move more and more into 3D, texturing 3D assets will be essential ☝️ Repainting 3D Assets is a new AI method that can take any 3D asset and paint it with a given text prompt. The results, while low-resolution, are pretty impressive.

Dreaming Tulpa 🥓👑

16,292 views • 2 years ago

the fact that i can take a random car image from google and turn it into a 3d asset in one go with ai is completely nuts to me
0:12

the fact that i can take a random car image from google and turn it into a 3d asset in one go with ai is completely nuts to me

Jan

72,355 views • 9 months ago

New Update: Minecraft 3D generation now in under 10s in falcraft⚡ Text → Image (FLUX.2 Klein) → 3D Gaussian splat (TripoSplat) → Voxelize → Minecraft structure! ~260k colored Gaussians are returned, we filter the faint ones, drop each into a voxel cell, average the color per cell and snap it into the nearest MC block in LAB color space
0:13

New Update: Minecraft 3D generation now in under 10s in falcraft⚡ Text → Image (FLUX.2 Klein) → 3D Gaussian splat (TripoSplat) → Voxelize → Minecraft structure! ~260k colored Gaussians are returned, we filter the faint ones, drop each into a voxel cell, average the color per cell and snap it into the nearest MC block in LAB color space

Blendi

31,757 views • 2 months ago

Not sure if this is old news, but I just discovered that in the Meta Quest browser you can longpress any image on any website and turn it into a 3D photo in a couple of seconds. I love it! Now I wish every image online worked like this by default.
0:15

Not sure if this is old news, but I just discovered that in the Meta Quest browser you can longpress any image on any website and turn it into a 3D photo in a couple of seconds. I love it! Now I wish every image online worked like this by default.

Morten Haulik ᯅ

13,017 views • 6 months ago

🚀 Smash The Mesh (STM) is a #GodotEngine add-on that lets you break 3D meshes into multiple pieces and apply physics to each fragment! Now in BETA, with caching for quick loading. Open-source and free to download! Get it here: 🔧 #Godot4 #GameDev
0:16

🚀 Smash The Mesh (STM) is a #GodotEngine add-on that lets you break 3D meshes into multiple pieces and apply physics to each fragment! Now in BETA, with caching for quick loading. Open-source and free to download! Get it here: 🔧 #Godot4 #GameDev

Claudio Z.

25,166 views • 2 years ago

Apologies for not posting in the past four days, I'm working hard🥹. I made a new system that allows you to shoulder Eno3's rifle ambidextrously and also pose it into the world. #VRChat
0:12

Apologies for not posting in the past four days, I'm working hard🥹. I made a new system that allows you to shoulder Eno3's rifle ambidextrously and also pose it into the world. #VRChat

Hyeon (graymore+)

14,602 views • 10 months ago

I've been working a lot with SAM3 and the Momentum Human Rig (MHR). I finally integrated it into the data I'm working with Rerun. The progression I've taken looks as follows SAM3 + SAM3D-body on 1. a single image 2. a set of multiple images 3. a single video 4. A multiview video capture I took inspiration from the SAM3D-body paper and built a multiview fitting optimization pipeline. This pipeline involves using the 2D keypoints from the single-view pipeline, triangulating them, and employing an L1 loss between the 2D/3D keypoints. The temporal stability isn't great, so that's the next portion I'm going to focus on. One really frustrating thing about SAM3D-body is the lack of per-joint confidence values. It makes it harder to deal with occlusions. I'm probably going to need to use a separate model, or maybe add a confidence head.
0:10

I've been working a lot with SAM3 and the Momentum Human Rig (MHR). I finally integrated it into the data I'm working with Rerun. The progression I've taken looks as follows SAM3 + SAM3D-body on 1. a single image 2. a set of multiple images 3. a single video 4. A multiview video capture I took inspiration from the SAM3D-body paper and built a multiview fitting optimization pipeline. This pipeline involves using the 2D keypoints from the single-view pipeline, triangulating them, and employing an L1 loss between the 2D/3D keypoints. The temporal stability isn't great, so that's the next portion I'm going to focus on. One really frustrating thing about SAM3D-body is the lack of per-joint confidence values. It makes it harder to deal with occlusions. I'm probably going to need to use a separate model, or maybe add a confidence head.

Pablo Vela

42,267 views • 7 months ago

🚨 I uploaded a random Pepsi logo... and 5 minutes later it was hanging from my bike. No CAD. No 3D skills. No complicated software. I found a tool called Hi3D that turns any 2D image into a printable 3D model instantly. What I made next got progressively more ridiculous 🧵
0:15

🚨 I uploaded a random Pepsi logo... and 5 minutes later it was hanging from my bike. No CAD. No 3D skills. No complicated software. I found a tool called Hi3D that turns any 2D image into a printable 3D model instantly. What I made next got progressively more ridiculous 🧵

Atul Kumar

103,181 views • 2 months ago

That awkward moment when you accidentally like a post… Today I wanted to share a new little slice-of-life scene I created with @MartiniArt_ via Seedance. I really like the fact that the whole workflow is centralized in one place.Importing 2D characters, converting them into 3D, creating reference shots, testing animations… Everything works through a node-based system, which makes it easy to get a clear overview and iterate quickly from one model to another.
0:16

That awkward moment when you accidentally like a post… Today I wanted to share a new little slice-of-life scene I created with @MartiniArt_ via Seedance. I really like the fact that the whole workflow is centralized in one place.Importing 2D characters, converting them into 3D, creating reference shots, testing animations… Everything works through a node-based system, which makes it easy to get a clear overview and iterate quickly from one model to another.

Anima

91,499 views • 5 months ago

🧍 Very cool idea So I added it to Photo AI as a T-Pose photo pack you can use to create a moving (or dancing) 3d model of yourself It auto-generates the correct T-Pose of your model immediately and then converts it into a 3D model you can download (as .fbx) and instantly import into valentina Mendez Mendez to rig it After rigging you can add any movement from Mixamo to move it however you want
1:28

🧍 Very cool idea So I added it to Photo AI as a T-Pose photo pack you can use to create a moving (or dancing) 3d model of yourself It auto-generates the correct T-Pose of your model immediately and then converts it into a 3D model you can download (as .fbx) and instantly import into valentina Mendez Mendez to rig it After rigging you can add any movement from Mixamo to move it however you want

@levelsio

140,555 views • 7 months ago

A preview of what's next, visualized with Rerun and PlayCanvas supersplat ✨ (Also, feel free to send me a DM 📩; I’ll be in San Francisco from July 21–29, and I'm looking to meet like-minded folks!) I'm convinced that Gaussian Splats will be an integral part of any data engine as an underlying representation. So I've started putting together a repo that: 1. Given a single image, perform image outpainting 🖼️🖌️ 2. Estimate a monocular depth map on the outpainted image 📏 3. Train a Gaussian Splat initialized from the monocular depth 🎓✨ 4. Warp to new views, perform inpainting on the missing masks -> Train new splat 🔄🎨 This is going to be integrated into exo-egoforge, but I wanted to start with the simple single-image version before moving to a multi-video implementation There's some weirdness in the final rerun visualization, but the trained splat looks great 🎉! This is all based on the very cool VistaDream paper ( .github.io/) More on this next week!
0:18

A preview of what's next, visualized with Rerun and PlayCanvas supersplat ✨ (Also, feel free to send me a DM 📩; I’ll be in San Francisco from July 21–29, and I'm looking to meet like-minded folks!) I'm convinced that Gaussian Splats will be an integral part of any data engine as an underlying representation. So I've started putting together a repo that: 1. Given a single image, perform image outpainting 🖼️🖌️ 2. Estimate a monocular depth map on the outpainted image 📏 3. Train a Gaussian Splat initialized from the monocular depth 🎓✨ 4. Warp to new views, perform inpainting on the missing masks -> Train new splat 🔄🎨 This is going to be integrated into exo-egoforge, but I wanted to start with the simple single-image version before moving to a multi-video implementation There's some weirdness in the final rerun visualization, but the trained splat looks great 🎉! This is all based on the very cool VistaDream paper ( .github.io/) More on this next week!

Pablo Vela

26,036 views • 1 year ago

Stitching a UFO video into a panorama makes it easier to see the overall apparent motion of the object (a black dot, starting in the lower right). But it also magnifies the parallax illusion, as the static background makes the camera motion less apparent.
0:19

Stitching a UFO video into a panorama makes it easier to see the overall apparent motion of the object (a black dot, starting in the lower right). But it also magnifies the parallax illusion, as the static background makes the camera motion less apparent.

Mick West

18,059 views • 2 months ago

Okay this new model is insane. Generate an image, then give it to the model to turn it into a 3D model with matching texture in seconds. Creativity on Spielwerk will be endless with this
0:10

Okay this new model is insane. Generate an image, then give it to the model to turn it into a 3D model with matching texture in seconds. Creativity on Spielwerk will be endless with this

Eike Drescher

37,987 views • 9 months ago

Damn it worked! Genie 3 world --> inpaint UI --> 4x topaz AI upscale --> train 3d gaussian splat You can step inside a painting of Socrates from 1787. Better than any image-to-3d model I've seen. I think Google has stumbled upon the killer app for VR -- the literal holodeck.
0:15

Damn it worked! Genie 3 world --> inpaint UI --> 4x topaz AI upscale --> train 3d gaussian splat You can step inside a painting of Socrates from 1787. Better than any image-to-3d model I've seen. I think Google has stumbled upon the killer app for VR -- the literal holodeck.

Bilawal Sidhu

658,477 views • 1 year ago

Who needs a mocap suit? 😁Testing out AIOS - All-in-One-Stage Expressive Human Pose and Shape Estimation (link in thread). I uploaded a video from Pexels and it created the 3D mesh, which I was able to import into Blender and use Geometry nodes to control. (see thread for nodes).
0:15

Who needs a mocap suit? 😁Testing out AIOS - All-in-One-Stage Expressive Human Pose and Shape Estimation (link in thread). I uploaded a video from Pexels and it created the 3D mesh, which I was able to import into Blender and use Geometry nodes to control. (see thread for nodes).

👣KᗪᗩᗯG👣 🔶

11,560 views • 1 year ago