正在加载视频...

视频加载失败

返回首页

Some more impressive 3D reconstruction examples from #DUSt3R kindly prepared by our boss ;-) Martin Humenberger NAVER LABS Europe

JeromeRevaud's profile picture

Jerome Revaud

1,673 subscribers

11,043 次观看 • 2 年前 •via X (Twitter)

#DUSt3R
LIVE

Anya Rossi• Live Now

Private livecam show

3 条评论

Jerome Revaud 的头像
Jerome Revaud2 年前

(the castle pic (second image pair) shows our actual Lab! )

BenderDrummer 的头像
BenderDrummer2 年前

@martinhu @naverlabseurope Even recent and historic lunar lander images would be a really interesting thing to recreate.. with @ILOA_Hawaii for example and the Odysseus mission

Jerome Revaud 的头像
Jerome Revaud2 年前

@martinhu @naverlabseurope @ILOA_Hawaii Yes, that would be interesting to see if earthly priors make sense on the moon too. 🌚 I guess it would, to some extent, because terrain on the moon looks like desert on earth…

相关视频

Instant Video-to-3D with DUST3R Dust3r generates a whole 3D scene from just a couple of images. What if it could: 1. Accept a VIDEO 2. Extract the video frames 3. Turn them into 3D? So added a Gradio Video Component. Here's me generating 3D from a video cc: NAVER LABS Europe
1:13

Instant Video-to-3D with DUST3R Dust3r generates a whole 3D scene from just a couple of images. What if it could: 1. Accept a VIDEO 2. Extract the video frames 3. Turn them into 3D? So added a Gradio Video Component. Here's me generating 3D from a video cc: NAVER LABS Europe

cocktail peanut

41,029 次观看 • 2 年前

A new model for human mesh recovery, high-performing and w/o using any 3D scans, has been published by my excellent colleagues at NAVER LABS Europe . Excellent work!
0:20

A new model for human mesh recovery, high-performing and w/o using any 3D scans, has been published by my excellent colleagues at NAVER LABS Europe . Excellent work!

Christian Wolf (🦋🦋🦋)

43,773 次观看 • 7 个月前

Marble is the first product from World Labs and is powered by our multimodal world model, which lets anyone create high-fidelity, persistent 3D worlds from just a single image, video, text prompt, or 3D layout. Read more at
0:51

Marble is the first product from World Labs and is powered by our multimodal world model, which lets anyone create high-fidelity, persistent 3D worlds from just a single image, video, text prompt, or 3D layout. Read more at

World Labs

117,016 次观看 • 7 个月前

Thrilled to share our new work on Reconviagen✨! A key challenge in 3D creation is the alignment of generative 3D with observational input. Our method solves this by grounding the generative process in 3D reconstruction. Try it at: #Reconstruction #AIGC
0:29

Thrilled to share our new work on Reconviagen✨! A key challenge in 3D creation is the alignment of generative 3D with observational input. Our method solves this by grounding the generative process in 3D reconstruction. Try it at: #Reconstruction #AIGC

Chongjie(CJ) Ye

11,614 次观看 • 9 个月前

She say that Africans imported technology, science, and astronomy from Africa to Europe. Some examples?
0:36

She say that Africans imported technology, science, and astronomy from Africa to Europe. Some examples?

RadioGenoa

125,801 次观看 • 8 个月前

📢Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction📢 -> highly accurate face reconstruction by training powerful VITs via surface normals and UV-coordinates estimation. The geometric cues from our 2D foundation model backbone constrain the 3DMM parameters, which allows us to achieve remarkable reconstruction accuracy - works for both single image and videos! In addition, we introduce a new 3D face reconstruction benchmark that evaluates both neutral and posed face geometry. 🌍 📷 Great work by Simon Giebenhain Tobias Kirschstein Martin Rünz Lourdes Agapito
0:32

📢Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction📢 -> highly accurate face reconstruction by training powerful VITs via surface normals and UV-coordinates estimation. The geometric cues from our 2D foundation model backbone constrain the 3DMM parameters, which allows us to achieve remarkable reconstruction accuracy - works for both single image and videos! In addition, we introduce a new 3D face reconstruction benchmark that evaluates both neutral and posed face geometry. 🌍 📷 Great work by Simon Giebenhain Tobias Kirschstein Martin Rünz Lourdes Agapito

Matthias Niessner

62,104 次观看 • 1 年前

VAST AI releases Triplane Meets Gaussian Splatting on Hugging Face Fast and Generalizable Single-View 3D Reconstruction with Transformers demo: TGS enables fast reconstruction from single-view image. It builds the 3D representation upon a hybrid Triplane-Gaussian representation by evaluating a transformer-based framework, from which 3D Gaussians would be decoded
0:23

VAST AI releases Triplane Meets Gaussian Splatting on Hugging Face Fast and Generalizable Single-View 3D Reconstruction with Transformers demo: TGS enables fast reconstruction from single-view image. It builds the 3D representation upon a hybrid Triplane-Gaussian representation by evaluating a transformer-based framework, from which 3D Gaussians would be decoded

AK

113,220 次观看 • 2 年前

"Africans brought so much technology, science and astronomy to Europe!" Some examples?
0:36

"Africans brought so much technology, science and astronomy to Europe!" Some examples?

RadioGenoa

166,748 次观看 • 1 年前

"AI Generated 3D is not production ready." The AI Generated 3D: 👇🙃 -- more (amazing) examples below. #GenAI #3D #GameArt
0:50

"AI Generated 3D is not production ready." The AI Generated 3D: 👇🙃 -- more (amazing) examples below. #GenAI #3D #GameArt

Emm | scenario.com

331,194 次观看 • 2 年前

3D Generalist Hirokazu Yokohara has experimented with Style3D CG's digital clothing solutions, showcasing some impressive real-time simulations. See more: #style3d #3d #3dart #3dsimulation #digitalclothing #realtime #unrealengine5 #ue5 #techart
0:29

3D Generalist Hirokazu Yokohara has experimented with Style3D CG's digital clothing solutions, showcasing some impressive real-time simulations. See more: #style3d #3d #3dart #3dsimulation #digitalclothing #realtime #unrealengine5 #ue5 #techart

80 LEVEL

33,767 次观看 • 2 年前

🚨 Paper Alert Our recent breakthrough CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image has been accepted by ACM SIGGRAPH 2025 Journal Track! CAST will change the way create scenes in 3D Art and Embody AI. 🚀Soon available at 👇Details
3:41

🚨 Paper Alert Our recent breakthrough CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image has been accepted by ACM SIGGRAPH 2025 Journal Track! CAST will change the way create scenes in 3D Art and Embody AI. 🚀Soon available at 👇Details

Deemos

34,110 次观看 • 1 年前

Sulaiman Ahmed Here’s some more examples
0:41

Sulaiman Ahmed Here’s some more examples

Suliman Al_sharrad ⚖

201,641 次观看 • 1 年前

📢📢GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction📢📢 Reconstructing high-fidelity 3D scenes from sparse RGB input is hard. It needs a strong 3D prior! We reformulate multi-view scene reconstruction as conditional 3D generation over overlapping spatial chunks, lifting posed image features into a generative shape prior via 3D conditioning. As an example prior, we build on Trellis2, and train it such that its reconstruction is pixel aligned and matches from all views. GenRecon achieves unprecedented reconstruction quality from any sparse RGB input sequence, even from a phone capture. The reconstruction also includes PBR materials which facilitates relighting and virtual object insertion. Amazing work by Katharina Schmid, Nicolas von Lützow, Jozef, Angela Dai
0:26

📢📢GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction📢📢 Reconstructing high-fidelity 3D scenes from sparse RGB input is hard. It needs a strong 3D prior! We reformulate multi-view scene reconstruction as conditional 3D generation over overlapping spatial chunks, lifting posed image features into a generative shape prior via 3D conditioning. As an example prior, we build on Trellis2, and train it such that its reconstruction is pixel aligned and matches from all views. GenRecon achieves unprecedented reconstruction quality from any sparse RGB input sequence, even from a phone capture. The reconstruction also includes PBR materials which facilitates relighting and virtual object insertion. Amazing work by Katharina Schmid, Nicolas von Lützow, Jozef, Angela Dai

Matthias Niessner

17,572 次观看 • 1 个月前

Some examples of our custom cursors nn
0:59

Some examples of our custom cursors nn

OTTIS 🇵🇪 -Comms open-

194,452 次观看 • 6 个月前

some more boss footage. this time from the 3rd phase
0:43

some more boss footage. this time from the 3rd phase

Felix Schade - Morbid Metal

78,388 次观看 • 3 年前

Got something to show for those who're curious to know more about my recent 3D Toon model style, here's some examples showing the Mickey Mouse and Minnie Mouse toon models! I'll also post more examples later on. Enjoy, my pals! #mickeymouse #art
2:02

Got something to show for those who're curious to know more about my recent 3D Toon model style, here's some examples showing the Mickey Mouse and Minnie Mouse toon models! I'll also post more examples later on. Enjoy, my pals! #mickeymouse #art

J.C. Thornton

34,220 次观看 • 5 个月前

A bit more GMS2 3D Sonic boss practice from this week, it's Metal's turn! (also a slightly more finalized moveset)
0:44

A bit more GMS2 3D Sonic boss practice from this week, it's Metal's turn! (also a slightly more finalized moveset)

Orca (orcaorcaorca in other words)

24,365 次观看 • 3 个月前

Combine Grok Imagine with Topaz Labs Astra. This keeps your creation intact but upgrades it to 60FPS and 1080p as a minimum to bring out more detail and motion. Astra works fully in your browser too. Some quick side-by-side examples.
0:24

Combine Grok Imagine with Topaz Labs Astra. This keeps your creation intact but upgrades it to 60FPS and 1080p as a minimum to bring out more detail and motion. Astra works fully in your browser too. Some quick side-by-side examples.

Jerrod Lew

35,809 次观看 • 8 个月前

Our One Pipeline strategy enables us to advance bold science, whether it comes from our own labs or from our collaborator’s labs.
0:35

Our One Pipeline strategy enables us to advance bold science, whether it comes from our own labs or from our collaborator’s labs.

Merck

10,017,231 次观看 • 2 个月前

More and more users are turning their 360 footage into fully explorable 3D Gaussian Splats with View it here: This reconstruction started from a simple capture and is now a fully explorable 3D Gaussian Splat rendered in the FreeGaussian viewer, complete with point cloud reconstruction and high-fidelity spatial detail. More and more creators are discovering that their existing footage can become immersive 3D scenes. And they’re doing it for free with FreeGaussian
0:58

More and more users are turning their 360 footage into fully explorable 3D Gaussian Splats with View it here: This reconstruction started from a simple capture and is now a fully explorable 3D Gaussian Splat rendered in the FreeGaussian viewer, complete with point cloud reconstruction and high-fidelity spatial detail. More and more creators are discovering that their existing footage can become immersive 3D scenes. And they’re doing it for free with FreeGaussian

Over the Reality 🌐

14,667 次观看 • 1 个月前