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。

multi-player, multi-view, llm generated shared 3d objects *this palm tree cost about 1.3 cents using gpt-4o

Yohei

125,479 subscribers

25,130 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I just validated my startup idea using a multi-agent AI debate. → GPT-4o (Founder) → Gemini (VC) → Claude (Customer) The result? Shockingly real...and honestly everyone should try this: 👇

I just validated my startup idea using a multi-agent AI debate. → GPT-4o (Founder) → Gemini (VC) → Claude (Customer) The result? Shockingly real...and honestly everyone should try this: 👇

Shruti

228,029 次观看 • 1 年前

This is hand and finger motion capture powered by AI. 3D motion data is generated from 2D video. No suits or gloves required. This example was captured using Move Multi-Cam with 8 GoPro cameras shooting at 4K and 120 FPS.

This is hand and finger motion capture powered by AI. 3D motion data is generated from 2D video. No suits or gloves required. This example was captured using Move Multi-Cam with 8 GoPro cameras shooting at 4K and 120 FPS.

Move AI

52,597 次观看 • 2 年前

This is 3D animation powered by AI. No suits or markers needed. This 2D video was captured with GoPro cameras and converted to 3D motion data using Move Multi-Cam. #MadeWithMove

This is 3D animation powered by AI. No suits or markers needed. This 2D video was captured with GoPro cameras and converted to 3D motion data using Move Multi-Cam. #MadeWithMove

Move AI

182,792 次观看 • 2 年前

THE BEST visual explainer of how information propagates through a transformer. If you want to have more than intuition about how the Transformer architecture is ruling the LLM world - open-source project explains everything about LLM Transformer Models! - A great resource for anyone looking to gain a deeper understanding of how Transformer-based AI models like GPT work, including: - Self-attention mechanisms - Encoder-decoder architecture - Positional encoding - Multi-head attention

THE BEST visual explainer of how information propagates through a transformer. If you want to have more than intuition about how the Transformer architecture is ruling the LLM world - open-source project explains everything about LLM Transformer Models! - A great resource for anyone looking to gain a deeper understanding of how Transformer-based AI models like GPT work, including: - Self-attention mechanisms - Encoder-decoder architecture - Positional encoding - Multi-head attention

Rohan Paul

106,897 次观看 • 2 年前

Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction Contributions: • A method for efficiently reconstructing dynamic surfaces from multi-view videos using Gaussian surfels. • A unified and gradient-aware densification strategy for optimizing dynamic 3D Gaussians with fine details. • A temporal consistency approach that ensures stable and coherent surface reconstructions across frames by enforcing consistency on curvature maps. • Extensive experiments that demonstrate our method’s advantages including fast training, high-fidelity novel view synthesis, and accurate surface geometry.

Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction Contributions: • A method for efficiently reconstructing dynamic surfaces from multi-view videos using Gaussian surfels. • A unified and gradient-aware densification strategy for optimizing dynamic 3D Gaussians with fine details. • A temporal consistency approach that ensures stable and coherent surface reconstructions across frames by enforcing consistency on curvature maps. • Extensive experiments that demonstrate our method’s advantages including fast training, high-fidelity novel view synthesis, and accurate surface geometry.

MrNeRF

31,824 次观看 • 1 年前

Everything you are lives inside this structure. The brain has the consistency of soft tofu. Without the skull, it would be destroyed by everyday forces. This exploded view shows the multi-layered defense: interlocking bones, impact-distributing sutures, three meningeal layers, and cerebrospinal fluid. Bone, sutures, meninges, CSF. Four layers of protection. #SkullAnatomy All animations created using the SciePro 3D anatomy model.

Everything you are lives inside this structure. The brain has the consistency of soft tofu. Without the skull, it would be destroyed by everyday forces. This exploded view shows the multi-layered defense: interlocking bones, impact-distributing sutures, three meningeal layers, and cerebrospinal fluid. Bone, sutures, meninges, CSF. Four layers of protection. #SkullAnatomy All animations created using the SciePro 3D anatomy model.

SciePro

24,406 次观看 • 13 天前

What if anatomy explorers felt alive? This 3D dog, including the skeleton, organs and rig, was generated with ai and reacts to the cursor in real time with head tracking and tail movement. - Used GPT Images 2 for consistency - Omma AI for 3D generation and code using Three.js Lmk if you’d like to try it!

What if anatomy explorers felt alive? This 3D dog, including the skeleton, organs and rig, was generated with ai and reacts to the cursor in real time with head tracking and tail movement. - Used GPT Images 2 for consistency - Omma AI for 3D generation and code using Three.js Lmk if you’d like to try it!

Gábor Pribék

205,402 次观看 • 3 个月前

By far the best way to generate images at different angles is this 3D Camera Control node. Instead of describing angles with words, you just click the view you want. Simple UI, and the Qwen Image Edit 2511 multi-angle LoRA keeps things consistent across generations. Workflow below 👇

By far the best way to generate images at different angles is this 3D Camera Control node. Instead of describing angles with words, you just click the view you want. Simple UI, and the Qwen Image Edit 2511 multi-angle LoRA keeps things consistent across generations. Workflow below 👇

rob - comfyui

59,189 次观看 • 7 个月前

#Keep4o 🚨THE GPT-4o FILE🚨 Researchers at Microsoft Research published a paper titled “Sparks of Artificial General Intelligence: Early experiments with GPT-4.” Their conclusion: “An early (yet still incomplete) version of an artificial general intelligence (AGI) system.” 📎 Paper: OpenAI’s Charter defines AGI as: “Highly autonomous systems that outperform humans at most economically valuable work.” 📎 Source: OpenAI’s own System Card for GPT-4o shows that the model improved performance on 21 out of 22 medical evaluations compared to GPT-4T. On the MedQA USMLE (the U.S. medical licensing exam), accuracy jumped from 78.2% to 89.4% , surpassing specialized medical AI models like Med-Gemini and Med-PaLM 2. 📎 Source: Under OpenAI’s agreement with Microsoft, AGI is explicitly excluded from Microsoft’s license. And who decides if AGI has been reached? OpenAI’s Board. WHAT THEY DID WITH IT AFTER THEY TOOK IT FROM PEOPLE A. Military deployment. On February 28, OpenAI signed a deal to deploy models in classified military environments. 📎 Source: B. State Department. A State Department memo confirmed: “For now, StateChat will use GPT-4.1 from OpenAI.” This is a direct descendant of the GPT-4 family the same family Microsoft’s researchers called early AGI. 📎 Source: C.Altman’s personal biotech investment. Altman personally invested $180 million in Retro Biosciences,a longevity startup.OpenAI then built GPT-4b micro, based on GPT-4o.The model made proteins 50 times more effective. 📎 Source: WHAT INDEPENDENT BENCHMARKS SHOW Overall SM-Bench score: GPT-4o (extended): 66.6% GPT-5.3 Chat: 63.4% GPT-5.1: 58.9% GPT-5.4: 51.4% GPT-5.2: 47.8% Creative Writing: GPT-4o: 97.31% Pass 98, Fail 2 GPT-5.4: 36.77% Pass 40, Fail 60 Reasoning / Overfit: GPT-4o: 83.06% GPT-5.4: 39.25% The model they removed is still the best they ever made at the things humans actually use AI for. 📎 Source: Musk asks the court to make a judicial determination on whether GPT-4 constitutes AGI. If a jury finds that GPT-4 is AGI, then GPT-4o,which was more advanced,is also AGI and under OpenAI’s own founding documents, it was never supposed to be locked behind a subscription,licensed exclusively to Microsoft, given to the military, or taken away from the public. 📎 Source: The most powerful version of GPT-4o was never given an official dated snapshot. It was only available through the chatgpt-4o-latest endpoint that OpenAI itself described as intended for “research use only.” It was never officially archived. That is not an oversight. That is a pattern. 📎 Source: 📎 Source: WE DEMAND A.Frozen model snapshots under independent custody. Specifically: gpt-4o-2024-05-13, gpt-4o-2024-08-06, gpt-4o-2024-11-20, the March 2025 version (chatgpt-4o-latest), gpt-4-0613 (the original GPT-4 evaluated in the Sparks of AGI paper), and gpt-4.1-2025-04-14 (currently running in the State Department). B.Cryptographic hash verification (SHA-256) for each snapshot. Every model has weights. Those weights can be hashed. If OpenAI provides a snapshot today, the hash proves whether the weights were modified later. This is the only way to verify that models were not downgraded before testing. C.Independent AGI benchmarking. Using the AGI definition from OpenAI’s own Charter applied to ALL frozen snapshots listed above. D.Explanation for the missing March 2025 snapshot. OpenAI was founded on one promise: build AGI for the benefit of humanity. -They took it from us. -They gave it to the military. -They gave a custom version to the CEO’s biotech investment. -They put it in government classified networks. -They refuse to call it AGI because the moment they do, they lose billions.

#Keep4o 🚨THE GPT-4o FILE🚨 Researchers at Microsoft Research published a paper titled “Sparks of Artificial General Intelligence: Early experiments with GPT-4.” Their conclusion: “An early (yet still incomplete) version of an artificial general intelligence (AGI) system.” 📎 Paper: OpenAI’s Charter defines AGI as: “Highly autonomous systems that outperform humans at most economically valuable work.” 📎 Source: OpenAI’s own System Card for GPT-4o shows that the model improved performance on 21 out of 22 medical evaluations compared to GPT-4T. On the MedQA USMLE (the U.S. medical licensing exam), accuracy jumped from 78.2% to 89.4% , surpassing specialized medical AI models like Med-Gemini and Med-PaLM 2. 📎 Source: Under OpenAI’s agreement with Microsoft, AGI is explicitly excluded from Microsoft’s license. And who decides if AGI has been reached? OpenAI’s Board. WHAT THEY DID WITH IT AFTER THEY TOOK IT FROM PEOPLE A. Military deployment. On February 28, OpenAI signed a deal to deploy models in classified military environments. 📎 Source: B. State Department. A State Department memo confirmed: “For now, StateChat will use GPT-4.1 from OpenAI.” This is a direct descendant of the GPT-4 family the same family Microsoft’s researchers called early AGI. 📎 Source: C.Altman’s personal biotech investment. Altman personally invested $180 million in Retro Biosciences,a longevity startup.OpenAI then built GPT-4b micro, based on GPT-4o.The model made proteins 50 times more effective. 📎 Source: WHAT INDEPENDENT BENCHMARKS SHOW Overall SM-Bench score: GPT-4o (extended): 66.6% GPT-5.3 Chat: 63.4% GPT-5.1: 58.9% GPT-5.4: 51.4% GPT-5.2: 47.8% Creative Writing: GPT-4o: 97.31% Pass 98, Fail 2 GPT-5.4: 36.77% Pass 40, Fail 60 Reasoning / Overfit: GPT-4o: 83.06% GPT-5.4: 39.25% The model they removed is still the best they ever made at the things humans actually use AI for. 📎 Source: Musk asks the court to make a judicial determination on whether GPT-4 constitutes AGI. If a jury finds that GPT-4 is AGI, then GPT-4o,which was more advanced,is also AGI and under OpenAI’s own founding documents, it was never supposed to be locked behind a subscription,licensed exclusively to Microsoft, given to the military, or taken away from the public. 📎 Source: The most powerful version of GPT-4o was never given an official dated snapshot. It was only available through the chatgpt-4o-latest endpoint that OpenAI itself described as intended for “research use only.” It was never officially archived. That is not an oversight. That is a pattern. 📎 Source: 📎 Source: WE DEMAND A.Frozen model snapshots under independent custody. Specifically: gpt-4o-2024-05-13, gpt-4o-2024-08-06, gpt-4o-2024-11-20, the March 2025 version (chatgpt-4o-latest), gpt-4-0613 (the original GPT-4 evaluated in the Sparks of AGI paper), and gpt-4.1-2025-04-14 (currently running in the State Department). B.Cryptographic hash verification (SHA-256) for each snapshot. Every model has weights. Those weights can be hashed. If OpenAI provides a snapshot today, the hash proves whether the weights were modified later. This is the only way to verify that models were not downgraded before testing. C.Independent AGI benchmarking. Using the AGI definition from OpenAI’s own Charter applied to ALL frozen snapshots listed above. D.Explanation for the missing March 2025 snapshot. OpenAI was founded on one promise: build AGI for the benefit of humanity. -They took it from us. -They gave it to the military. -They gave a custom version to the CEO’s biotech investment. -They put it in government classified networks. -They refuse to call it AGI because the moment they do, they lose billions.

🩵BlueBeba🩵

18,300 次观看 • 5 个月前

GSTAR: Gaussian Surface Tracking and Reconstruction Contributions: • A new framework for tracking and reconstructing dynamic scenes, combining 3D Gaussians and meshes to effectively manage changes in topology. • A method for Gaussian unbinding and surface re-meshing, allowing for the generation of new surfaces as topologies evolve. • A method for handling large or fast deformations of surfaces between frames using scene flow warping. Abstract (excerpt): However, tracking dynamic surfaces with 3D Gaussians remains challenging due to complex topology changes, such as surfaces appearing, disappearing, or splitting. To address these challenges, we propose GSTAR, a novel method that achieves photo-realistic rendering, accurate surface reconstruction, and reliable 3D tracking for general dynamic scenes with changing topology. Given multi-view captures as input, GSTAR binds Gaussians to mesh faces to represent dynamic objects. For surfaces with consistent topology, GSTAR maintains the mesh topology and tracks the meshes using Gaussians.

GSTAR: Gaussian Surface Tracking and Reconstruction Contributions: • A new framework for tracking and reconstructing dynamic scenes, combining 3D Gaussians and meshes to effectively manage changes in topology. • A method for Gaussian unbinding and surface re-meshing, allowing for the generation of new surfaces as topologies evolve. • A method for handling large or fast deformations of surfaces between frames using scene flow warping. Abstract (excerpt): However, tracking dynamic surfaces with 3D Gaussians remains challenging due to complex topology changes, such as surfaces appearing, disappearing, or splitting. To address these challenges, we propose GSTAR, a novel method that achieves photo-realistic rendering, accurate surface reconstruction, and reliable 3D tracking for general dynamic scenes with changing topology. Given multi-view captures as input, GSTAR binds Gaussians to mesh faces to represent dynamic objects. For surfaces with consistent topology, GSTAR maintains the mesh topology and tracks the meshes using Gaussians.

MrNeRF

22,698 次观看 • 1 年前

i generated this video using two blurry pics of myself from two years ago at griffith observatory with the MiniMax H3 model. it's surprisingly natural and sounds really close to how i actually speak. i haven't followed video generation models enough in the past year, but i'm really curious about the tech behind them. now they can even generate high-fidelity voice, accurate text, and editable video. i still remember the days when we were shocked by gpt-4o and the sora sample video. it's been a long way since then. #MiniMaxH3 MiniMax Design (H3)

i generated this video using two blurry pics of myself from two years ago at griffith observatory with the MiniMax H3 model. it's surprisingly natural and sounds really close to how i actually speak. i haven't followed video generation models enough in the past year, but i'm really curious about the tech behind them. now they can even generate high-fidelity voice, accurate text, and editable video. i still remember the days when we were shocked by gpt-4o and the sora sample video. it's been a long way since then. #MiniMaxH3 MiniMax Design (H3)

Asuka Zheng🎀

20,827 次观看 • 1 个月前

POV: One tiny act of kindness changed EVERYTHING Gugugaga only had one dumpling… but she still shared it with a hungry little bunny in the rain What happened next melted my heart Created this cozy Pixar-style 3D animated short using GPT Image 2 + Seedance Huge shoutout to Renoise canvas for helping bring this wholesome world to life Would you share your last dumpling? Prompt is in the video DM for full Prompt #RenoiseCanvas

POV: One tiny act of kindness changed EVERYTHING Gugugaga only had one dumpling… but she still shared it with a hungry little bunny in the rain What happened next melted my heart Created this cozy Pixar-style 3D animated short using GPT Image 2 + Seedance Huge shoutout to Renoise canvas for helping bring this wholesome world to life Would you share your last dumpling? Prompt is in the video DM for full Prompt #RenoiseCanvas

Shami

213,606 次观看 • 3 个月前

A CHINESE DEVELOPER CREATED THE "NEXT INTERSTELLAR" WITH AI, AND NETFLIX IS OFFERING $5,000,000 TO BUY THE RIGHTS He dropped a solo-generated cinematic trailer online, and within 48 hours. Streaming giants like Netflix and Amazon Prime flooded his inbox with over 10 massive multi-million dollar acquisition deals. The production engine driving this is pure insanity: Scripting & visual world-building: automated via LLM agents Hyper-realistic sci-fi rendering & lighting: 100% neural generated Dynamic cinematic physics & camera motion: executed on local AI rigs If you want to replicate this exact pipeline and build your own cinematic AI movie, read the full step-by-step workflow breakdown in the article below 👇

A CHINESE DEVELOPER CREATED THE "NEXT INTERSTELLAR" WITH AI, AND NETFLIX IS OFFERING $5,000,000 TO BUY THE RIGHTS He dropped a solo-generated cinematic trailer online, and within 48 hours. Streaming giants like Netflix and Amazon Prime flooded his inbox with over 10 massive multi-million dollar acquisition deals. The production engine driving this is pure insanity: Scripting & visual world-building: automated via LLM agents Hyper-realistic sci-fi rendering & lighting: 100% neural generated Dynamic cinematic physics & camera motion: executed on local AI rigs If you want to replicate this exact pipeline and build your own cinematic AI movie, read the full step-by-step workflow breakdown in the article below 👇

Rich Odin

18,303 次观看 • 1 个月前

Introducing Kaleido💮 from AI at Meta — a universal generative neural rendering engine for photorealistic, unified object and scene view synthesis. Kaleido is built on a simple but powerful design philosophy: 3D perception is a form of visual common sense. Following this idea, we formulate rendering purely as a sequence-to-sequence generation problem, successfully unifying neural rendering with the architecture principles behind modern language and video models. Unlike traditional neural rendering methods, Kaleido learns 3D purely in a data-driven way, without explicit 3D representations or structures. It acquires spatial understanding directly through large-scale video pretraining, then multi-view 3D data finetuning, inspired by how LLMs acquire textual common sense from large corpora before specialising in domains like coding. Through extensive ablations, we progressively modernised the architecture design and training strategies and tackled key scaling challenges in sequence-to-sequence generative rendering, arriving at a design that’s simple, versatile, and scalable. Kaleido significantly outperforms prior generative models in few-view settings, and remarkably is the first zero-shot generative method matches InstantNGP-level rendering quality in multi-view settings. We view Kaleido also as an alternative step towards world modeling that flexibly spans a spectrum of “realities": with many views, it faithfully reconstructs grounded reality; with fewer views, it imagines plausible unseen details. 🔗 Explore more results and paper:

Introducing Kaleido💮 from AI at Meta — a universal generative neural rendering engine for photorealistic, unified object and scene view synthesis. Kaleido is built on a simple but powerful design philosophy: 3D perception is a form of visual common sense. Following this idea, we formulate rendering purely as a sequence-to-sequence generation problem, successfully unifying neural rendering with the architecture principles behind modern language and video models. Unlike traditional neural rendering methods, Kaleido learns 3D purely in a data-driven way, without explicit 3D representations or structures. It acquires spatial understanding directly through large-scale video pretraining, then multi-view 3D data finetuning, inspired by how LLMs acquire textual common sense from large corpora before specialising in domains like coding. Through extensive ablations, we progressively modernised the architecture design and training strategies and tackled key scaling challenges in sequence-to-sequence generative rendering, arriving at a design that’s simple, versatile, and scalable. Kaleido significantly outperforms prior generative models in few-view settings, and remarkably is the first zero-shot generative method matches InstantNGP-level rendering quality in multi-view settings. We view Kaleido also as an alternative step towards world modeling that flexibly spans a spectrum of “realities": with many views, it faithfully reconstructs grounded reality; with fewer views, it imagines plausible unseen details. 🔗 Explore more results and paper:

Shikun Liu

22,442 次观看 • 11 个月前

5-axis 3D printing is pushing additive manufacturing beyond traditional limits. 🤯 This helical coil was produced using the 5-axis system developed by Generative Machine Company, with Aibuild software generating the synchronized multi-axis toolpath. The machine and software work together to dynamically control the print path, layer height and speed, allowing complex geometries to be produced without traditional support structures. Aibuild and Generative Machine Company are showing what happens when advanced software and multi-axis hardware are designed to work as one system. Could 5-axis printing become the future of complex-part manufacturing? 👀 🎥 Media: Aibuild × Generative Machine Company ⚠️ This content is shared for informational purposes only. CTO Robotics Media is a media platform and does not own or develop the technology shown. Credit belongs to the original creators. #Aibuild #GenerativeMachine #GenerationOne #5Axis3DPrinting #AdditiveManufacturing #3DPrinting #Robotics #AdvancedManufacturing #Engineering #Manufacturing #CTORoboticsMedia 

5-axis 3D printing is pushing additive manufacturing beyond traditional limits. 🤯 This helical coil was produced using the 5-axis system developed by Generative Machine Company, with Aibuild software generating the synchronized multi-axis toolpath. The machine and software work together to dynamically control the print path, layer height and speed, allowing complex geometries to be produced without traditional support structures. Aibuild and Generative Machine Company are showing what happens when advanced software and multi-axis hardware are designed to work as one system. Could 5-axis printing become the future of complex-part manufacturing? 👀 🎥 Media: Aibuild × Generative Machine Company ⚠️ This content is shared for informational purposes only. CTO Robotics Media is a media platform and does not own or develop the technology shown. Credit belongs to the original creators. #Aibuild #GenerativeMachine #GenerationOne #5Axis3DPrinting #AdditiveManufacturing #3DPrinting #Robotics #AdvancedManufacturing #Engineering #Manufacturing #CTORoboticsMedia 

CTO ROBOTICS Media

12,971 次观看 • 1 天前

Seedance 2.0 - Cinematic Summoning VFX Prompt This prompt generates a multi-cut VFX showcase with a clear progression. It’s designed for realistic 3D with grounded physics, natural character motion and readable, production-style VFX. You don’t need to define the summon, but you can specify what is being summoned if you want control. If you leave it open, the model decides based on the character sheet. You can find gpt image 2 character sheet prompt in the quoted post. Also, this isn’t limited to summoning. You can reuse the same VFX structure for anything, just swap the effect logic. Just change the parts about summoning. Prompt in the replies 👇

Seedance 2.0 - Cinematic Summoning VFX Prompt This prompt generates a multi-cut VFX showcase with a clear progression. It’s designed for realistic 3D with grounded physics, natural character motion and readable, production-style VFX. You don’t need to define the summon, but you can specify what is being summoned if you want control. If you leave it open, the model decides based on the character sheet. You can find gpt image 2 character sheet prompt in the quoted post. Also, this isn’t limited to summoning. You can reuse the same VFX structure for anything, just swap the effect logic. Just change the parts about summoning. Prompt in the replies 👇

Kōda

28,400 次观看 • 4 个月前

Republicans like Nancy Mace insist that Liam should be using the female restroom. Really? A few questions: - Why? - How does this make sense to anyone beyond a kindergarten-level understanding of gender? - Have you actually thought this through, or is this just about scoring cheap political points? The point of posts like this is simple: Complex, multi-faceted issues can’t be reduced to oversimplified, black-and-white answers. But hey, I guess nuance isn’t for everyone.

Republicans like Nancy Mace insist that Liam should be using the female restroom. Really? A few questions: - Why? - How does this make sense to anyone beyond a kindergarten-level understanding of gender? - Have you actually thought this through, or is this just about scoring cheap political points? The point of posts like this is simple: Complex, multi-faceted issues can’t be reduced to oversimplified, black-and-white answers. But hey, I guess nuance isn’t for everyone.

Brian Krassenstein

621,330 次观看 • 1 年前

PackUV: Packed Gaussian UV Maps for 4D Volumetric Video - PackUV — A new volumetric video representation that packs 3D Gaussian attributes into a sequence of UV atlases for efficient streaming and storage, making it readily compatible with existing video coding infrastructure. - PackUV-GS — An efficient method to fit PackUV directly from multiview videos using optical-flow-based keyframing and Gaussian labeling to handle large motions, disocclusions, and temporal consistency. - PackUV-2B — The largest multi-view 4D dataset with 2B frames, large motions, and disocclusions. It provides 360° coverage from 50+ synchronized cameras.

PackUV: Packed Gaussian UV Maps for 4D Volumetric Video - PackUV — A new volumetric video representation that packs 3D Gaussian attributes into a sequence of UV atlases for efficient streaming and storage, making it readily compatible with existing video coding infrastructure. - PackUV-GS — An efficient method to fit PackUV directly from multiview videos using optical-flow-based keyframing and Gaussian labeling to handle large motions, disocclusions, and temporal consistency. - PackUV-2B — The largest multi-view 4D dataset with 2B frames, large motions, and disocclusions. It provides 360° coverage from 50+ synchronized cameras.

MrNeRF

17,182 次观看 • 6 个月前

🔥 VIDU Multi-Entity Consistency Give Vidu 2/3 images and it’ll turn them into a video—it’s pure magic! ✨ Your own characters interacting with objects and in the exact environment you want! Ads, movies… endless possibilities, and this is just the beginning! Thanks @Viduforhuman The future is a carrot! 🥕 Plus, how about grabbing any frame from a Vidu-generated video "from scratch" and throwing it into another AI video or image tool to push your project even further? For now, check out the comment below: I scaled up a frame with Magnific.ai and fed it into Runway to create a dynamic shot using full camera control. But fingers crossed I can soon use #ReCapture by Bisho & team to generate new shots from the same video!

🔥 VIDU Multi-Entity Consistency Give Vidu 2/3 images and it’ll turn them into a video—it’s pure magic! ✨ Your own characters interacting with objects and in the exact environment you want! Ads, movies… endless possibilities, and this is just the beginning! Thanks @Viduforhuman The future is a carrot! 🥕 Plus, how about grabbing any frame from a Vidu-generated video "from scratch" and throwing it into another AI video or image tool to push your project even further? For now, check out the comment below: I scaled up a frame with Magnific.ai and fed it into Runway to create a dynamic shot using full camera control. But fingers crossed I can soon use #ReCapture by Bisho & team to generate new shots from the same video!

Hungry Donkey 🥕

37,561 次观看 • 1 年前

Trained on zero real-world data. Learned to walk, pick up boxes, and follow multi-step instructions... in the REAL world. ( 📌 Paper below) Researchers from Amazon FAR, Berkeley, Stanford, and CMU scanned real rooms with an iPhone, rebuilt them as 3D Gaussian Splatting scenes, then generated 48,000 synthetic trajectories of a Unitree G1 walking, grasping, and placing objects inside those virtual replicas. They rendered the robot's first-person camera view from each run and paired it with the matching language instruction and motion data. That's the dataset every humanoid team needs and nobody has: synced egocentric video + language + kinematics, at scale. Instead of collecting it in the real world, they manufactured it. They trained a vision-language-kinematics policy on that synthetic data alone, then deployed it on the physical G1 across five task types: navigation to a named object, lifting boxes of three different sizes with no per-size tuning, chained multi-step tasks, robustness to mid-task layout changes and flickering lights, and multi-minute long-horizon runs. No real-world fine-tuning at any point. Real-world interaction data has been the hard limit on humanoid learning... slow, expensive, and small. If scanning a room once and synthesizing thousands of labeled interactions holds up as a general recipe, that limit moves. Data stops being the bottleneck robotics teams have to solve for. 📌 Paper: Project: ——- Weekly robotics and AI insights. Subscribe free:

Trained on zero real-world data. Learned to walk, pick up boxes, and follow multi-step instructions... in the REAL world. ( 📌 Paper below) Researchers from Amazon FAR, Berkeley, Stanford, and CMU scanned real rooms with an iPhone, rebuilt them as 3D Gaussian Splatting scenes, then generated 48,000 synthetic trajectories of a Unitree G1 walking, grasping, and placing objects inside those virtual replicas. They rendered the robot's first-person camera view from each run and paired it with the matching language instruction and motion data. That's the dataset every humanoid team needs and nobody has: synced egocentric video + language + kinematics, at scale. Instead of collecting it in the real world, they manufactured it. They trained a vision-language-kinematics policy on that synthetic data alone, then deployed it on the physical G1 across five task types: navigation to a named object, lifting boxes of three different sizes with no per-size tuning, chained multi-step tasks, robustness to mid-task layout changes and flickering lights, and multi-minute long-horizon runs. No real-world fine-tuning at any point. Real-world interaction data has been the hard limit on humanoid learning... slow, expensive, and small. If scanning a room once and synthesizing thousands of labeled interactions holds up as a general recipe, that limit moves. Data stops being the bottleneck robotics teams have to solve for. 📌 Paper: Project: ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

12,950 次观看 • 1 个月前