Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

SplatOverflow: Asynchronous Hardware Troubleshooting TL;DR: That's probably the most creative application of 3DGS I have ever seen :) Abstract (excerpt): SplatOverflow creates a novel boundary object, the SplatOverflow scene, that users reference to communicate about hardware. The scene comprises a 3D Gaussian Splat of the user’s hardware registered onto... show more

MrNeRF

16,937 subscribers

20,141 görüntüleme • 2 yıl önce •via X (Twitter)

Bilim & Teknoloji Eğitim Haberler & Politika

Anya Rossi• Live Now

Private livecam show

4 Yorum

MrNeRF profil fotoğrafı

MrNeRF2 yıl önce

Paper:

Tom Bielecki profil fotoğrafı

Tom Bielecki2 yıl önce

@josefprusa remote troubleshoot mechanical issues on a Prusa printer using 3D scanning :)

____tansh profil fotoğrafı

____tansh2 yıl önce

Thanks for sharing!

MrNeRF profil fotoğrafı

MrNeRF2 yıl önce

You are welcome!

Benzer Videolar

A few months ago, Kyle McDonald sent me a message with a simple idea: capture my workspace as a Gaussian Splat, put a monitor back into that same space, track the viewer and make the monitor disappear. It’s been on my to-do list ever since... I finally built a POC… Working name: Vitre. It turns a screen into a window onto a 3D capture of the space it is actually in. My office space was captured as a 3D Gaussian Splat and registered back into the physical space. A camera tracks the viewer’s position, and the scene is rendered from that point of view in real time. Move around the screen and the perspective changes with you, as if you were looking through a window. Still a POC. The calibration of the whole system needs to be more precise, and there’s still some noticeable latency between the tracking and the render. #3DGS #GaussianSplatting #ComputerVision

A few months ago, Kyle McDonald sent me a message with a simple idea: capture my workspace as a Gaussian Splat, put a monitor back into that same space, track the viewer and make the monitor disappear. It’s been on my to-do list ever since... I finally built a POC… Working name: Vitre. It turns a screen into a window onto a 3D capture of the space it is actually in. My office space was captured as a 3D Gaussian Splat and registered back into the physical space. A camera tracks the viewer’s position, and the scene is rendered from that point of view in real time. Move around the screen and the perspective changes with you, as if you were looking through a window. Still a POC. The calibration of the whole system needs to be more precise, and there’s still some noticeable latency between the tracking and the render. #3DGS #GaussianSplatting #ComputerVision

Hugues Bruyère

37,114 görüntüleme • 1 ay önce

Watch the story of how the Model Hardware Standard began as part of our collaboration with HHMI

Watch the story of how the Model Hardware Standard began as part of our collaboration with HHMI

Anthropic

208,991 görüntüleme • 2 ay önce

Agents have reached hardware. We are launching Flow v3, the Agentic Platform for Physical Engineering. We've spent over a year building it in secret, alongside the best hardware companies and AI research labs. An agent can now do real engineering work: change a requirement, push the update into your CAD and simulation tools, and flag every test that needs to rerun. Iterations/learning cycles that took months are being reduced to days. Agents are the biggest shift in how we engineer hardware since CAD. The core innovation for the CAD era was the parametric model. The core innovation for the Agentic Era is Flow's Systems Graph. The systems graph is a living model of every requirement, design model, test, analysis and every connection between them. It gives every agent the full context of the system, so every change stays consistent across the whole design. Engineers and agents work side by side on the same system. Engineers get to focus on architecture - the decisions that matter -while thousands of agents churn through rewriting reports, rerunning analysis and simulation, and triggering tests. Reusable rockets, self-driving cars, small modular reactors, robots that make decisions, the most complex machines ever built, are defined by millions of interconnected requirements, far beyond what any human team can keep aligned on its own. Rivian, Joby, Astranis, Skydio, Radiant, and the most ambitious hardware programs already build on Flow. More on the launch in the comments. @buildonfloweng

Agents have reached hardware. We are launching Flow v3, the Agentic Platform for Physical Engineering. We've spent over a year building it in secret, alongside the best hardware companies and AI research labs. An agent can now do real engineering work: change a requirement, push the update into your CAD and simulation tools, and flag every test that needs to rerun. Iterations/learning cycles that took months are being reduced to days. Agents are the biggest shift in how we engineer hardware since CAD. The core innovation for the CAD era was the parametric model. The core innovation for the Agentic Era is Flow's Systems Graph. The systems graph is a living model of every requirement, design model, test, analysis and every connection between them. It gives every agent the full context of the system, so every change stays consistent across the whole design. Engineers and agents work side by side on the same system. Engineers get to focus on architecture - the decisions that matter -while thousands of agents churn through rewriting reports, rerunning analysis and simulation, and triggering tests. Reusable rockets, self-driving cars, small modular reactors, robots that make decisions, the most complex machines ever built, are defined by millions of interconnected requirements, far beyond what any human team can keep aligned on its own. Rivian, Joby, Astranis, Skydio, Radiant, and the most ambitious hardware programs already build on Flow. More on the launch in the comments. @buildonfloweng

Pari Singh

41,905 görüntüleme • 5 ay önce

I believe vibe manufacturing will create thousands of companies that make $1M or more a year. In 2024, Lovable and Bolt made anyone a vibe coder. Now the same shift happens for physical products, and OpenAI's Astra was the first model of this era. Before, a hardware product meant your team needed a full-time 3D designer, a mechanical engineer, and an electrical engineer. Now you pay $20 a month for a frontier model to walk you through all of it. The market for your product can be small. If it costs little to make, there is a business. Hardware looked too hard to me. I did not know it, so I did not try. Now I have a hardware desk on the way. Make one thing: a printable object, a CAD file, a Blender model, or a circuit board. You owe it to yourself.

I believe vibe manufacturing will create thousands of companies that make $1M or more a year. In 2024, Lovable and Bolt made anyone a vibe coder. Now the same shift happens for physical products, and OpenAI's Astra was the first model of this era. Before, a hardware product meant your team needed a full-time 3D designer, a mechanical engineer, and an electrical engineer. Now you pay $20 a month for a frontier model to walk you through all of it. The market for your product can be small. If it costs little to make, there is a business. Hardware looked too hard to me. I did not know it, so I did not try. Now I have a hardware desk on the way. Make one thing: a printable object, a CAD file, a Blender model, or a circuit board. You owe it to yourself.

The Startup Ideas Podcast (SIP) 🧃

75,856 görüntüleme • 1 ay önce

Exclusive | Zoo: Text-to-CAD w/ @theJordanNoone AI Revolutionizes Hardware Development Jordan dives into: - Why Zoo started by building a novel geometry engine - How the founding team’s background led to Zoo’s products - The impact of generative AI on hardware design - Zoo’s expansion from software for hardware design, to software for the full hardware development cycle - Why they open sourced their software Full pod, memo, slides from their deck, docs, & more linked in Sourcery below

Exclusive | Zoo: Text-to-CAD w/ @theJordanNoone AI Revolutionizes Hardware Development Jordan dives into: - Why Zoo started by building a novel geometry engine - How the founding team’s background led to Zoo’s products - The impact of generative AI on hardware design - Zoo’s expansion from software for hardware design, to software for the full hardware development cycle - Why they open sourced their software Full pod, memo, slides from their deck, docs, & more linked in Sourcery below

Molly O’Shea

76,119 görüntüleme • 2 yıl önce

There's actually a lot of companies in East Asia that offer LiDAR hardware solutions alongside GS with BIM integration- CAD overlayed with well-calibrated / unwarped Gaussian Splats for aesthetic viewing. I seldom hear about these things in the US though

There's actually a lot of companies in East Asia that offer LiDAR hardware solutions alongside GS with BIM integration- CAD overlayed with well-calibrated / unwarped Gaussian Splats for aesthetic viewing. I seldom hear about these things in the US though

Towaki Takikawa / 瀧川永遠希

22,440 görüntüleme • 1 yıl önce

Easily the coolest and most impressive demo of a 4D gaussian splat i have seen so far. Kudos to the team Btw it's directly on their landing page

Easily the coolest and most impressive demo of a 4D gaussian splat i have seen so far. Kudos to the team Btw it's directly on their landing page

Andreas Klinger 🦾

54,813 görüntüleme • 3 ay önce

SF Compute CEO evan conrad explains why GPU clusters are bad collateral for lenders: "This article was more of a prediction of a trend that is already happening. I probably should’ve said, currently, most startups cannot buy compute. It is only getting harder and harder and harder." "If you want to finance a GPU cluster, you need to first have collateral, which is typically the hardware itself. The problem with that collateral is nobody wants to buy the hardware. They want to buy the hardware in a data center that’s operated by a company that works." "And the situation in which you recoup that hardware is often the situation in which the person operating that hardware is just as likely to blow up. There’s a lot of correlated risk." "If you are the startup trying to buy a cluster, to the eyes of a lender, you look like you’re gonna blow up." San Francisco Compute

SF Compute CEO evan conrad explains why GPU clusters are bad collateral for lenders: "This article was more of a prediction of a trend that is already happening. I probably should’ve said, currently, most startups cannot buy compute. It is only getting harder and harder and harder." "If you want to finance a GPU cluster, you need to first have collateral, which is typically the hardware itself. The problem with that collateral is nobody wants to buy the hardware. They want to buy the hardware in a data center that’s operated by a company that works." "And the situation in which you recoup that hardware is often the situation in which the person operating that hardware is just as likely to blow up. There’s a lot of correlated risk." "If you are the startup trying to buy a cluster, to the eyes of a lender, you look like you’re gonna blow up." San Francisco Compute

MTS

17,810 görüntüleme • 16 gün önce

In the Orbit of Solaris – A gaussian splat reconstruction of a scene from Tarkovsky’s masterpiece

In the Orbit of Solaris – A gaussian splat reconstruction of a scene from Tarkovsky’s masterpiece

Benjamin Bardou

44,792 görüntüleme • 8 ay önce

We introduced Text-to-CAD into our Modeling App to allow hardware designers to use prompts in addition to the traditional point and click style they are used to. We also have a third method, CAD represented as code, for users who want it. I expand on the code approach here. 🧵

We introduced Text-to-CAD into our Modeling App to allow hardware designers to use prompts in addition to the traditional point and click style they are used to. We also have a third method, CAD represented as code, for users who want it. I expand on the code approach here. 🧵

Jordan Noone 🇺🇸

48,471 görüntüleme • 1 yıl önce

Parris: Why would I still want an Xbox? Phil Spencer: "I want people to pick hardware based on the capabilities of that hardware and how that fits into the choices they want to make about where they want to play and we want our hardware to win based on the hardware capability abilities that we have." "It's really game first not platform first most of the games you and I will talk about run across so many different platforms and those are the games that are having success those are the games that are at the top of the charts when you look at the most played most successful games." "I want to build a platform that services those creators those creators that are trying to meet people on every screen. Let's say like our own hardware, I think it's fundamental to what Xbox is. It's not lost on me, I've said over and over that box is in the name of our brand. I'll say is in the position I'm in I look at Hardware as a critical part of what we do."

VGT Gaming News

157,458 görüntüleme • 1 yıl önce

The largest advancement of the CUDA platform since its creation in 2006 is here 👀 Introducing CUDA Tile, a tile-based programming model that provides the ability to write algorithms at a higher level and abstract away the details of specialized hardware, such as tensor cores. Read the technical blog 👉

The largest advancement of the CUDA platform since its creation in 2006 is here 👀 Introducing CUDA Tile, a tile-based programming model that provides the ability to write algorithms at a higher level and abstract away the details of specialized hardware, such as tensor cores. Read the technical blog 👉

NVIDIA AI Developer

244,885 görüntüleme • 11 ay önce

Jeff Dean says he's bullish on specialized hardware because a handful of workloads will be a lot of the world's compute "I'm pretty bullish on more and more specialized hardware, because I think that's the way you really get much more efficient systems." "And we now have workloads where there's like a handful of workloads that are going to be a lot of the compute in the world." "And so if you think about that, that is crying out for specialization." "The problem with specialization is if what you want to do changes in the future, then the thing you've lovingly crafted in hardware for maybe two years is no longer perhaps as relevant."

Jeff Dean says he's bullish on specialized hardware because a handful of workloads will be a lot of the world's compute "I'm pretty bullish on more and more specialized hardware, because I think that's the way you really get much more efficient systems." "And we now have workloads where there's like a handful of workloads that are going to be a lot of the compute in the world." "And so if you think about that, that is crying out for specialization." "The problem with specialization is if what you want to do changes in the future, then the thing you've lovingly crafted in hardware for maybe two years is no longer perhaps as relevant."

Fireside Alpha

105,480 görüntüleme • 1 ay önce

Today, we're releasing HW-Bench, the first hardware engineering benchmark built in partnership with the world's most advanced hardware companies. Measurement has always been core to our work at Arena Physica: the very first version of Atlas shipped with our internal framework for evaluating frontier models on real hardware engineering tasks. HW-Bench evaluates frontier model performance on production hardware data and captures the full hardware context across tools and file formats. Each task is graded against rubrics and golden answers reviewed by subject matter experts at our partner companies, who build some of the most advanced hardware in the world, from the chips behind modern supercomputing to the autonomous systems and vessels redefining defense at sea and beyond (more coming soon). We'll be building towards jobs that span disciplines, like designing, manufacturing, and testing a 140 GHz, 512-element D-band phased array. To start, see how 15 frontier models performed at designing a 2.45 GHz antenna at

Today, we're releasing HW-Bench, the first hardware engineering benchmark built in partnership with the world's most advanced hardware companies. Measurement has always been core to our work at Arena Physica: the very first version of Atlas shipped with our internal framework for evaluating frontier models on real hardware engineering tasks. HW-Bench evaluates frontier model performance on production hardware data and captures the full hardware context across tools and file formats. Each task is graded against rubrics and golden answers reviewed by subject matter experts at our partner companies, who build some of the most advanced hardware in the world, from the chips behind modern supercomputing to the autonomous systems and vessels redefining defense at sea and beyond (more coming soon). We'll be building towards jobs that span disciplines, like designing, manufacturing, and testing a 140 GHz, 512-element D-band phased array. To start, see how 15 frontier models performed at designing a 2.45 GHz antenna at

Arena Physica

13,458 görüntüleme • 8 gün önce

A 3D Gaussian Splat by David "Navi" Romero of the aftermath of a huge fire in Denver. Unlike a standard 2D video, the splat allows us to fly through the wreckage of the largest fire Denver has seen in decades. SuperSplat Link👇

A 3D Gaussian Splat by David "Navi" Romero of the aftermath of a huge fire in Denver. Unlike a standard 2D video, the splat allows us to fly through the wreckage of the largest fire Denver has seen in decades. SuperSplat Link👇

Will Eastcott

15,640 görüntüleme • 10 ay önce

Painting with 3D Gaussian Splat Brushes Contributions: • Designing a set of interactive tools and brush parameters for artistic brush creation and control using 3DGS content. • Computing oriented 3D Gaussian splat brushes for stamp-based painting on 3D surfaces represented as meshes or 3DGS scenes. • Deforming the splats in a brush stamp to ensure a smooth appearance of the painted 3D stroke. • Producing seamless brush strokes despite overlapping brush stamps, using diffusion inpainting. • Efficient modeling and rendering of brush strokes to facilitate 3DGS painting in real time.

Painting with 3D Gaussian Splat Brushes Contributions: • Designing a set of interactive tools and brush parameters for artistic brush creation and control using 3DGS content. • Computing oriented 3D Gaussian splat brushes for stamp-based painting on 3D surfaces represented as meshes or 3DGS scenes. • Deforming the splats in a brush stamp to ensure a smooth appearance of the painted 3D stroke. • Producing seamless brush strokes despite overlapping brush stamps, using diffusion inpainting. • Efficient modeling and rendering of brush strokes to facilitate 3DGS painting in real time.

MrNeRF

23,096 görüntüleme • 1 yıl önce

Embedder (YC S25) just launched the world's first hardware-aware coding agent. By understanding and interacting directly with your hardware, it achieves state of the art performance in an embedded systems (C/C++) context. Embedder

Embedder (YC S25) just launched the world's first hardware-aware coding agent. By understanding and interacting directly with your hardware, it achieves state of the art performance in an embedded systems (C/C++) context. Embedder

Ethan Gibbs

708,808 görüntüleme • 1 yıl önce

Introducing Zenith - talk to build hardware. Build hardware projects at the speed of intent. Link in the comments.

Introducing Zenith - talk to build hardware. Build hardware projects at the speed of intent. Link in the comments.

Harish

66,936 görüntüleme • 10 ay önce

Software is dead.... so I'm pivoting to hardware With the power of AI, I'm building my own AI speaker Am I hardware engineer? Is this the next wave? This was the most fun I've had in a video

Software is dead.... so I'm pivoting to hardware With the power of AI, I'm building my own AI speaker Am I hardware engineer? Is this the next wave? This was the most fun I've had in a video

Micky

36,186 görüntüleme • 7 gün önce