Sensitive content

This media may contain sensitive content.

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。

Researchers presented Vid2Avatar, a method that creates human avatars from in-the-wild videos via self-supervised scene decomposition. See more: #AI #ArtificialIntelligence #3dart #research

80 LEVEL

262,459 subscribers

247,468 次观看 • 3 年前 •via X (Twitter)

NSFW #AI #ArtificialIntelligence #3dart #research

Anya Rossi• Live Now

Private livecam show

9 条评论

MR3D-Dev 的头像

MR3D-Dev3 年前

So instead of a giant green screen I should just go to a soccer field, thanks for the idea.

Karet 的头像

Karet3 年前

When they tell you to act normal

InfinityCg 的头像

InfinityCg3 年前

All this shit and still no automatic UVs 😭

BADASS Studios 的头像

BADASS Studios3 年前

This would be really interesting to see implemented in a metaverse platform. Imagine the digital dance parties!

kivanc 的头像

kivanc3 年前

Is that real time normal map?

Lazer Eyes 的头像

Lazer Eyes3 年前

he look normal

Squaremusher 的头像

Squaremusher3 年前

Did we just skip mocap altogether?

Tioaoa 的头像

Tioaoa3 年前

O hell yeh Nonstop!

_man_Art_man_ 的头像

_man_Art_man_3 年前

Woooooow!!! That is awesome and crazy !!! Switch it ON for all !! We do not longer need bloody rigs 😅😅😅

相关视频

Adobe presents SynCHMR! A method that can reconstruct camera trajectory, human motion, and scene in one global coordinate from videos 🔥

Adobe presents SynCHMR! A method that can reconstruct camera trajectory, human motion, and scene in one global coordinate from videos 🔥

Dreaming Tulpa 🥓👑

108,628 次观看 • 2 年前

We're stepping into a new reality (!) Introducing EMO: a groundbreaking AI that creates expressive portrait videos from just an image and audio! 🧵 More in the thread:

We're stepping into a new reality (!) Introducing EMO: a groundbreaking AI that creates expressive portrait videos from just an image and audio! 🧵 More in the thread:

Dogan Ural

414,041 次观看 • 2 年前

Joe Rogan discusses how top abduction researchers all relied on the highly questionable method of regressive hypnotic therapy. The entire foundation of abduction research comes from a method even psychologists consider unreliable.

Joe Rogan discusses how top abduction researchers all relied on the highly questionable method of regressive hypnotic therapy. The entire foundation of abduction research comes from a method even psychologists consider unreliable.

Astral🛸

29,502 次观看 • 7 个月前

Using #AugmentedReality in Human Anatomy via @Analytics_659 #AI #ArtificialIntelligence #VR #AR #VirtualReality cc: John C. Maxwell, III @ronald_vanloon Pascal Bornet Marcus Borba

Using #AugmentedReality in Human Anatomy via @Analytics_659 #AI #ArtificialIntelligence #VR #AR #VirtualReality cc: John C. Maxwell, III @ronald_vanloon Pascal Bornet Marcus Borba

Ronald van Loon

18,702 次观看 • 3 年前

Researchers have developed a method that enables three-dimensional RNA analysis at cellular resolution in intact mouse brains. The new method can transform our understanding of brain function. Research by Per Uhlén, Shigeaki_Kanatani, et al. Published in Science Magazine.

Researchers have developed a method that enables three-dimensional RNA analysis at cellular resolution in intact mouse brains. The new method can transform our understanding of brain function. Research by Per Uhlén, Shigeaki_Kanatani, et al. Published in Science Magazine.

Karolinska Institutet

60,523 次观看 • 1 年前

🚀New from Meta FAIR: today we’re introducing Seamless Interaction, a research project dedicated to modeling interpersonal dynamics. The project features a family of audiovisual behavioral models, developed in collaboration with Meta’s Codec Avatars lab + Core AI lab, that render speech between two individuals into diverse, expressive full-body gestures and active listening behaviors, allowing the creation of fully embodied avatars in 2D and 3D. These models have potential to create more natural, interactive virtual agents that can engage in human-like social interactions across a variety of settings. Learn more:

🚀New from Meta FAIR: today we’re introducing Seamless Interaction, a research project dedicated to modeling interpersonal dynamics. The project features a family of audiovisual behavioral models, developed in collaboration with Meta’s Codec Avatars lab + Core AI lab, that render speech between two individuals into diverse, expressive full-body gestures and active listening behaviors, allowing the creation of fully embodied avatars in 2D and 3D. These models have potential to create more natural, interactive virtual agents that can engage in human-like social interactions across a variety of settings. Learn more:

AI at Meta

48,410 次观看 • 1 年前

Trade research drudgery for research breakthroughs — @SciSpace_ Agent gives back an average of 1300 hours a year to researchers. SciSpace Agent is the first #AI built exclusively for the scientific research community. Learn more about your new AI co-scientist in this thread.

Trade research drudgery for research breakthroughs — @SciSpace_ Agent gives back an average of 1300 hours a year to researchers. SciSpace Agent is the first #AI built exclusively for the scientific research community. Learn more about your new AI co-scientist in this thread.

Kirk Borne

11,871 次观看 • 11 个月前

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

Hila Chefer

67,589 次观看 • 3 个月前

Nvidia CEO Huang points out 3 reasons why China will win in AI: 🔸China has a large and dynamic market. 🔸China has 50% of the world's AI researchers. 🔸AI is being applied to everything from consumer applications, internet shopping, grocery delivery to self-driving cars... A huge market creates huge demands that can accumulate huge experience for improvement.

Nvidia CEO Huang points out 3 reasons why China will win in AI: 🔸China has a large and dynamic market. 🔸China has 50% of the world's AI researchers. 🔸AI is being applied to everything from consumer applications, internet shopping, grocery delivery to self-driving cars... A huge market creates huge demands that can accumulate huge experience for improvement.

Li Zexin 李泽欣

76,778 次观看 • 11 个月前

It's been a huge day for AI with announcements from Alibaba, Lightricks, Ideogram, Apple, Adobe, OpenAI, and more. The 7 most important developments that happened: 1. Alibaba researchers unveiled EMO, an AI that adds lip-syncing to videos.

It's been a huge day for AI with announcements from Alibaba, Lightricks, Ideogram, Apple, Adobe, OpenAI, and more. The 7 most important developments that happened: 1. Alibaba researchers unveiled EMO, an AI that adds lip-syncing to videos.

Rowan Cheung

703,184 次观看 • 2 年前

Introducing “FlowMap”, the first self-supervised, differentiable structure-from-motion method that is competitive with conventional SfM like Colmap! IMO this solves a major missing piece for internet-scale training of 3D Deep Learning methods. 1/n

Introducing “FlowMap”, the first self-supervised, differentiable structure-from-motion method that is competitive with conventional SfM like Colmap! IMO this solves a major missing piece for internet-scale training of 3D Deep Learning methods. 1/n

Vincent Sitzmann

128,573 次观看 • 2 年前

🦓 Self-supervised multimodal ML is promising the next AI breakthrough - in our new work published in nature, we debut @CEBRAai: for self-supervised hypothesis- and discovery-driven science. 📝 💻 🦓 🧵⬇️

🦓 Self-supervised multimodal ML is promising the next AI breakthrough - in our new work published in nature, we debut @CEBRAai: for self-supervised hypothesis- and discovery-driven science. 📝 💻 🦓 🧵⬇️

Mackenzie Weygandt Mathis, PhD

248,769 次观看 • 3 年前

UK has officially launched the state’s FIRST Bachelor of Science in Artificial Intelligence. Watch to see how we’re leading the way in AI. Learn more here: #AI #ArtificialIntelligence #UKY #UKEngineering #Innovation

UK has officially launched the state’s FIRST Bachelor of Science in Artificial Intelligence. Watch to see how we’re leading the way in AI. Learn more here: #AI #ArtificialIntelligence #UKY #UKEngineering #Innovation

University of Kentucky

16,120 次观看 • 4 个月前

Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: • We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up framework aggregates and transforms per-frame 3D Gaussian Splats into a cohesive scene representation, enabling self-supervised motion estimation. Furthermore, we introduce motion tokens that capture common motion primitives and regularize motion predictions, facilitating dynamic motion group segmentation without explicit motion or correspondence supervision. • We present several enhancements for in-the-wild scenarios, including sky modeling, camera exposure inconsistency handling, large novel-view extrapolation, and fine-grained human motions reconstruction, making STORM well-suited for real-world applications.

Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: • We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up framework aggregates and transforms per-frame 3D Gaussian Splats into a cohesive scene representation, enabling self-supervised motion estimation. Furthermore, we introduce motion tokens that capture common motion primitives and regularize motion predictions, facilitating dynamic motion group segmentation without explicit motion or correspondence supervision. • We present several enhancements for in-the-wild scenarios, including sky modeling, camera exposure inconsistency handling, large novel-view extrapolation, and fine-grained human motions reconstruction, making STORM well-suited for real-world applications.

MrNeRF

53,292 次观看 • 1 年前

Introducing Avatars in ElevenCreative. The best AI voices, now with a face. Create studio-grade talking videos from a script, a voice, and an avatar - all in one place.

ElevenLabs

397,198 次观看 • 14 天前

Researchers have reached a new milestone in the future of organ transplantation: a modified pig kidney transplanted into a human has been successfully functioning for 32 consecutive days. Learn more about Dr. Robert Montgomery’s research:

Researchers have reached a new milestone in the future of organ transplantation: a modified pig kidney transplanted into a human has been successfully functioning for 32 consecutive days. Learn more about Dr. Robert Montgomery’s research:

NYU Langone Health

12,295 次观看 • 2 年前

Ron Howard breaks down the wild stunt scene with Seth Rogen in “The Studio." | Variety Making a Scene presented by HBO

Ron Howard breaks down the wild stunt scene with Seth Rogen in “The Studio." | Variety Making a Scene presented by HBO

Variety

43,222 次观看 • 1 年前

AI creates “South Park” characters in human form 😳

AI creates “South Park” characters in human form 😳

Daily Loud

2,691,079 次观看 • 3 年前