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.

Most 3DGS segmentation tools either pre‑train per scene or lock errors into a feature field you can’t undo. ArtisanGS instead turns a few 2D masks into editable 3D object selections via Cutie tracking + black‑box splat aggregation, then lets you iteratively correct mistakes with consistent 2D/3D selection modes. 📗... show more

NVIDIA AI Developer

111,523 subscribers

42,281 views • 4 months 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

Segment Any 3D Gaussians paper page: Interactive 3D segmentation in radiance fields is an appealing task since its importance in 3D scene understanding and manipulation. However, existing methods face challenges in either achieving fine-grained, multi-granularity segmentation or contending with substantial computational overhead, inhibiting real-time interaction. In this paper, we introduce Segment Any 3D GAussians (SAGA), a novel 3D interactive segmentation approach that seamlessly blends a 2D segmentation foundation model with 3D Gaussian Splatting (3DGS), a recent breakthrough of radiance fields. SAGA efficiently embeds multi-granularity 2D segmentation results generated by the segmentation foundation model into 3D Gaussian point features through well-designed contrastive training. Evaluation on existing benchmarks demonstrates that SAGA can achieve competitive performance with state-of-the-art methods. Moreover, SAGA achieves multi-granularity segmentation and accommodates various prompts, including points, scribbles, and 2D masks. Notably, SAGA can finish the 3D segmentation within milliseconds, achieving nearly 1000x acceleration compared to previous SOTA.

Segment Any 3D Gaussians paper page: Interactive 3D segmentation in radiance fields is an appealing task since its importance in 3D scene understanding and manipulation. However, existing methods face challenges in either achieving fine-grained, multi-granularity segmentation or contending with substantial computational overhead, inhibiting real-time interaction. In this paper, we introduce Segment Any 3D GAussians (SAGA), a novel 3D interactive segmentation approach that seamlessly blends a 2D segmentation foundation model with 3D Gaussian Splatting (3DGS), a recent breakthrough of radiance fields. SAGA efficiently embeds multi-granularity 2D segmentation results generated by the segmentation foundation model into 3D Gaussian point features through well-designed contrastive training. Evaluation on existing benchmarks demonstrates that SAGA can achieve competitive performance with state-of-the-art methods. Moreover, SAGA achieves multi-granularity segmentation and accommodates various prompts, including points, scribbles, and 2D masks. Notably, SAGA can finish the 3D segmentation within milliseconds, achieving nearly 1000x acceleration compared to previous SOTA.

AK

69,542 views • 2 years ago

How to turn any 2d object into 3d!

How to turn any 2d object into 3d!

xarr

59,259 views • 1 year ago

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Bilawal Sidhu

92,792 views • 2 years ago

My game's weirdest feature explained in 5 words or less - You're a 2D in a 3D

My game's weirdest feature explained in 5 words or less - You're a 2D in a 3D

Chronoscript 【Official】

5,293,695 views • 6 months ago

🥇 1st place: "3D shaper" by Konstantin Zolozhkov 3D shaper lets you draw shapes in 2D that then gets turned into 3D objects App link: 🎁 Prize: $1,000 worth of Lovable credits + $500 worth of Supabase credits + Lovable & Supabase swag

🥇 1st place: "3D shaper" by Konstantin Zolozhkov 3D shaper lets you draw shapes in 2D that then gets turned into 3D objects App link: 🎁 Prize: $1,000 worth of Lovable credits + $500 worth of Supabase credits + Lovable & Supabase swag

Lovable

26,268 views • 1 year ago

SAM 3D Body is a CVPR 2026 award candidate paper from AI at Meta model recovers a full 3D human body mesh from a single RGB image you can run it automatically, or guide the reconstruction with masks and 2D keypoints thx to Niels Rogge for awesome demo idea

SAM 3D Body is a CVPR 2026 award candidate paper from AI at Meta model recovers a full 3D human body mesh from a single RGB image you can run it automatically, or guide the reconstruction with masks and 2D keypoints thx to Niels Rogge for awesome demo idea

SkalskiP

71,881 views • 25 days ago

one 2d photo --> 3d gaussian splat quick test with Echo-2 by SpAItial -- these 3d scene generation models are getting better! already at a sufficient quality to serve as a virtual set / backdrop in your 3d tool of choice

one 2d photo --> 3d gaussian splat quick test with Echo-2 by SpAItial -- these 3d scene generation models are getting better! already at a sufficient quality to serve as a virtual set / backdrop in your 3d tool of choice

Bilawal Sidhu

23,511 views • 2 months ago

YOU CAN NOW REMASTER ANY 2D GAME INTO A 3D WORLD Pokémon Ruby defined a generation of top-down handheld gaming. 2D is fast and solo-friendly: tiles, sprites, simple animations. 3D has always been brutal modeling, rigging, lighting, LODs, and months of specialized work that kills most small teams. Mint shatters that One screenshot → instant coherent 3D worlds No more waiting for studios to invest a 2D game becomes 3D today.

YOU CAN NOW REMASTER ANY 2D GAME INTO A 3D WORLD Pokémon Ruby defined a generation of top-down handheld gaming. 2D is fast and solo-friendly: tiles, sprites, simple animations. 3D has always been brutal modeling, rigging, lighting, LODs, and months of specialized work that kills most small teams. Mint shatters that One screenshot → instant coherent 3D worlds No more waiting for studios to invest a 2D game becomes 3D today.

mint

16,280 views • 23 days ago

Having another cookie? It's a "3D Photo", a Gaussian splat. #3dgs

Having another cookie? It's a "3D Photo", a Gaussian splat. #3dgs

Dany Bittel

50,975 views • 6 months ago

Comp breakdown. 🤗 Character is 3D. Background is a 2D painting (photoshop) VFX are 2D (Animate) #blender #animation #p2design #2D #3D

Comp breakdown. 🤗 Character is 3D. Background is a 2D painting (photoshop) VFX are 2D (Animate) #blender #animation #p2design #2D #3D

Pierrick Picaut

47,226 views • 10 months ago

Started experimenting with eye jiggle physics in warudo, trying to get that 2d look into 3d!!

Started experimenting with eye jiggle physics in warudo, trying to get that 2d look into 3d!!

icebell 🍨🔔

34,797 views • 2 years ago

NVIDIA finally released Neuralangelo's source code! The model can turn videos from any device into detailed 3D structures, fully replicating buildings, sculptures, or other real aworld objects or spaces virtually. Here's how it works: A model utilizes a 2D video with multiple angles of an object or scene. I selects frames from different viewpoints to understand depth, size, and shape. The AI creates an initial 3D representation, similar to a sculptor shaping a subject. The render is optimized to enhance details, like a sculptor refining texture. The outcome is a 3D object or scene suitable for virtual reality, digital twins, or robotics.

NVIDIA finally released Neuralangelo's source code! The model can turn videos from any device into detailed 3D structures, fully replicating buildings, sculptures, or other real aworld objects or spaces virtually. Here's how it works: A model utilizes a 2D video with multiple angles of an object or scene. I selects frames from different viewpoints to understand depth, size, and shape. The AI creates an initial 3D representation, similar to a sculptor shaping a subject. The render is optimized to enhance details, like a sculptor refining texture. The outcome is a 3D object or scene suitable for virtual reality, digital twins, or robotics.

Lior Alexander

478,018 views • 2 years ago

SpatialTracker Tracking Any 2D Pixels in 3D Space Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process, leading to occlusions and discontinuities in the 2D motion domain.

SpatialTracker Tracking Any 2D Pixels in 3D Space Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process, leading to occlusions and discontinuities in the 2D motion domain.

AK

77,162 views • 2 years ago

Is your game 2D or 3D? Yes

Is your game 2D or 3D? Yes

SmellyFrog

27,520 views • 1 year ago

Is your game 2D or 3D? yes

Is your game 2D or 3D? yes

Azurexis🧡 - 🐥PAPER ANIMAL ADVENTURE OUT NOW!🐢

11,997 views • 11 months ago

Ed Catmull (Pixar founder) just joined Odyssey's board as they reveal their first 3D breakthrough: Instantly turning any 2D image into an editable 3D world. World Labs isn't alone anymore. Here's the TL;DR without the hype 🧵

Ed Catmull (Pixar founder) just joined Odyssey's board as they reveal their first 3D breakthrough: Instantly turning any 2D image into an editable 3D world. World Labs isn't alone anymore. Here's the TL;DR without the hype 🧵

Bilawal Sidhu

161,629 views • 1 year ago

Painting over a 3d sculpt Taking a simple 3D base and turning it into final 2d artwork Sculpted in ZBrush + Nomad Sculpt Rendered in Keyshot Overpainted in Photoshop

Painting over a 3d sculpt Taking a simple 3D base and turning it into final 2d artwork Sculpted in ZBrush + Nomad Sculpt Rendered in Keyshot Overpainted in Photoshop

Anna Balashova

49,789 views • 9 months ago

2D janja with 3D janja

2D janja with 3D janja

Janja 🍰☕ (Fortnite arc)

17,996 views • 2 years ago

A 2D being trying to comprehend 3D

A 2D being trying to comprehend 3D

𝙄𝙧𝙤𝙗𝙪𝙨𝙩🇦🇱#TENOÍ

4,039,294 views • 4 months ago