正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

We used machine learning to quickly recreate key moments from the World Cup in 3D using just a single photograph. Read about our process:

NYTimes R&D

13,235 subscribers

100,678 次观看 • 3 年前 •via X (Twitter)

科学技术新闻政治

Anya Rossi• Live Now

Private livecam show

4 条评论

Karan Ganesan 的头像

Karan Ganesan3 年前

@ajchavar well done!👌 so cool to see ♥️ @theatre_js in action @ariaminaei

Rafael Höhr 🇪🇺 的头像

Rafael Höhr 🇪🇺3 年前

Absolutely amazing👏👏👏 !!!!!!!! Why did not have this 20 and 10 years ago!, we could have escaped from the newsroom to see the sunlight 😂. Thank you so much. #infographics @elpais_info @ST_Graphics

Cameron Horst 的头像

Cameron Horst3 年前

@memdotai mem it

Iván Cárdenas 的头像

Iván Cárdenas3 年前

@SaveToNotion #tweet #3D #MachineLearning

相关视频

In the final episode of our series 'Inside The World Cup' we look back at the key moments from England's tournament as Thomas Tuchel's side claimed a bronze medal 🏴󠁧󠁢󠁥󠁮󠁧󠁿

In the final episode of our series 'Inside The World Cup' we look back at the key moments from England's tournament as Thomas Tuchel's side claimed a bronze medal 🏴󠁧󠁢󠁥󠁮󠁧󠁿

ITV Football

4,507,362 次观看 • 25 天前

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

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

117,310 次观看 • 9 个月前

I’m using Unity + ComfyUI to recreate those PSX-style JRPG 3D world maps, but generating the terrain in real time

I’m using Unity + ComfyUI to recreate those PSX-style JRPG 3D world maps, but generating the terrain in real time

Cristian Peñas ░░░░░░░░

223,372 次观看 • 9 个月前

#Onthisday in 1983, "Photograph" was released as a single in the UK. The lead single from our third studio album, Pyromania 🔥

#Onthisday in 1983, "Photograph" was released as a single in the UK. The lead single from our third studio album, Pyromania 🔥

Def Leppard

41,469 次观看 • 6 个月前

I generated this 3D enviroment using a single image using "Marble" from World Labs. The new version can generate a mesh from the splat and is directly usable in Unreal Engine 5.7.

I generated this 3D enviroment using a single image using "Marble" from World Labs. The new version can generate a mesh from the splat and is directly usable in Unreal Engine 5.7.

Matt Workman

42,460 次观看 • 9 个月前

Building a machine learning model isn’t just about finding the right algorithm—it’s about the right process. In Machine Learning in Production, Andrew Ng breaks down the iterative loop of model development: training, error analysis, refining hyperparameters, and improving data. Getting to a high test set accuracy is one thing, but aligning your model with real-world business metrics? That’s where the real challenge begins. Learn how to bridge the gap between models and impact:

Building a machine learning model isn’t just about finding the right algorithm—it’s about the right process. In Machine Learning in Production, Andrew Ng breaks down the iterative loop of model development: training, error analysis, refining hyperparameters, and improving data. Getting to a high test set accuracy is one thing, but aligning your model with real-world business metrics? That’s where the real challenge begins. Learn how to bridge the gap between models and impact:

DeepLearning.AI

45,248 次观看 • 1 年前

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

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 Ye

11,624 次观看 • 11 个月前

Every single final clip you see in this video was rendered with Ray3 Modify in Dream Machine by Luma. Each clip originating from a handcrafted 3D scene. This is a glimpses of the 3D/VFX workflows of the future, keeping the parts we love and making the whole process more efficient and limitless.

Every single final clip you see in this video was rendered with Ray3 Modify in Dream Machine by Luma. Each clip originating from a handcrafted 3D scene. This is a glimpses of the 3D/VFX workflows of the future, keeping the parts we love and making the whole process more efficient and limitless.

Luma | Dream Lab

32,071 次观看 • 7 个月前

Helix is now learning directly from human video data We have already trained on data collected in the real world, including Brookfield residential units To our knowledge, this is the first instance of a humanoid robot learning navigation end-to-end using only human video

Helix is now learning directly from human video data We have already trained on data collected in the real world, including Brookfield residential units To our knowledge, this is the first instance of a humanoid robot learning navigation end-to-end using only human video

Figure

46,041 次观看 • 11 个月前

At 18 years old, around about 1990/91 and just a few years into learning 3D graphics I worked with a friend, the late Jose Commins to create our first 3D world on the Atari ST. It might seem primitive and crude, but this was a foundational step for me from there to #NoMansSky

At 18 years old, around about 1990/91 and just a few years into learning 3D graphics I worked with a friend, the late Jose Commins to create our first 3D world on the Atari ST. It might seem primitive and crude, but this was a foundational step for me from there to #NoMansSky

Martin Griffiths

34,936 次观看 • 1 年前

Introducing a new approach for editing images, now live in the Auto frame feature in Google Photos. Our method interprets 2D photos as 3D scenes, allowing you to re-capture moments from a new perspective after the photos have been taken. Read all about it:

Introducing a new approach for editing images, now live in the Auto frame feature in Google Photos. Our method interprets 2D photos as 3D scenes, allowing you to re-capture moments from a new perspective after the photos have been taken. Read all about it:

Google Research

24,069 次观看 • 3 个月前

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

AI at Meta

17,858 次观看 • 8 个月前

I just used Luma's text-to-3D to generate a DeLorean from Back to the Future and placed it in my living room using the Vision Pro! The future is wild. 🤩

I just used Luma's text-to-3D to generate a DeLorean from Back to the Future and placed it in my living room using the Vision Pro! The future is wild. 🤩

Ammaar Reshi

265,555 次观看 • 2 年前

We also present another paper at @SIGGRAPH 2023 on neural implicit 3D Morphable Models that can be used to create a dynamic 3D avatar from a single in-the-wild image. (Lead author Connor Lin).

Koki Nagano

12,776 次观看 • 3 年前

We’ve submitted our hackathon project! To grasp small tools, we made an adapter using a 3D printer and repeatedly trained our ACT-based policy with imitation learning — resulting in our robotic TeaMaster :wink: #LeRobotWorldwideHackathon #lerobot

We’ve submitted our hackathon project! To grasp small tools, we made an adapter using a 3D printer and repeatedly trained our ACT-based policy with imitation learning — resulting in our robotic TeaMaster :wink: #LeRobotWorldwideHackathon #lerobot

taguromaru / JK1RZI

38,838 次观看 • 1 年前

These firefighters rushed out to an emergency call just moments before a crucial penalty kick in the World Cup.

These firefighters rushed out to an emergency call just moments before a crucial penalty kick in the World Cup.

Historic Vids

960,267 次观看 • 2 年前

"Dangerous Heat Threatens the 2026 FIFA World Cup" - read more about this, and other major news in sustainability and climate change in the latest Sustainability Bulletin. To read the report, see the link in our bio 🔗

"Dangerous Heat Threatens the 2026 FIFA World Cup" - read more about this, and other major news in sustainability and climate change in the latest Sustainability Bulletin. To read the report, see the link in our bio 🔗

Al-Attiyah Foundation

203,400 次观看 • 2 个月前

Using Proto Hologram, we can live-beam guests from anywhere in the world for real-time, interactive learning experiences! 🌍 This gives students and staff access to professionals who they may otherwise not have the chance to engage with. Read more ➡️

Using Proto Hologram, we can live-beam guests from anywhere in the world for real-time, interactive learning experiences! 🌍 This gives students and staff access to professionals who they may otherwise not have the chance to engage with. Read more ➡️

Loughborough University

11,536 次观看 • 2 年前